junyanz

Professional software vendor delivering innovative solutions on the Softono platform. Specialized in both open-source and proprietary software development.

Visit Website

Total Products

Software by junyanz

Open Source

pytorch-CycleGAN-and-pix2pix

<img src='imgs/horse2zebra.gif' align="right" width=384> <br><br><br> # CycleGAN and pix2pix in PyTorch **Udpate in 2025**: we recently updated the code to support Python 3.11 and PyTorch 2.4. It also supports DDP for single-machine multiple-GPU training. (Please use `torchrun --nproc_per_node=4 train.py ...`) **New**: Please check out [img2img-turbo](https://github.com/GaParmar/img2img-turbo) repo that includes both pix2pix-turbo and CycleGAN-Turbo. Our new one-step image-to-image translation methods can support both paired and unpaired training and produce better results by leveraging the pre-trained StableDiffusion-Turbo model. The inference time for 512x512 image is 0.29 sec on A6000 and 0.11 sec on A100. Please check out [contrastive-unpaired-translation](https://github.com/taesungp/contrastive-unpaired-translation) (CUT), our new unpaired image-to-image translation model that enables fast and memory-efficient training. We provide PyTorch implementations for both unpaired and paired image-to-image translation. The code was written by [Jun-Yan Zhu](https://github.com/junyanz) and [Taesung Park](https://github.com/taesungp), and supported by [Tongzhou Wang](https://github.com/SsnL). This PyTorch implementation produces results comparable to or better than our original Torch software. If you would like to reproduce the same results as in the papers, check out the original [CycleGAN Torch](https://github.com/junyanz/CycleGAN) and [pix2pix Torch](https://github.com/phillipi/pix2pix) code in Lua/Torch. **Note**: The current software works well with PyTorch 2.4+. Check out the older [branch](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/tree/pytorch0.3.1) that supports PyTorch 0.1-0.3. You may find useful information in [training/test tips](docs/tips.md) and [frequently asked questions](docs/qa.md). To implement custom models and datasets, check out our [templates](#custom-model-and-dataset). To help users better understand and adapt our codebase, we provide an [overview](docs/overview.md) of the code structure of this repository. **CycleGAN: [Project](https://junyanz.github.io/CycleGAN/) | [Paper](https://arxiv.org/pdf/1703.10593.pdf) | [Torch](https://github.com/junyanz/CycleGAN) | [Tensorflow Core Tutorial](https://www.tensorflow.org/tutorials/generative/cyclegan) | [PyTorch Colab](https://colab.research.google.com/github/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/CycleGAN.ipynb)** <img src="https://junyanz.github.io/CycleGAN/images/teaser_high_res.jpg" width="800"/> **Pix2pix: [Project](https://phillipi.github.io/pix2pix/) | [Paper](https://arxiv.org/pdf/1611.07004.pdf) | [Torch](https://github.com/phillipi/pix2pix) | [Tensorflow Core Tutorial](https://www.tensorflow.org/tutorials/generative/pix2pix) | [PyTorch Colab](https://colab.research.google.com/github/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/pix2pix.ipynb)** <img src="https://phillipi.github.io/pix2pix/images/teaser_v3.png" width="800px"/> **[EdgesCats Demo](https://affinelayer.com/pixsrv/) | [pix2pix-tensorflow](https://github.com/affinelayer/pix2pix-tensorflow) | by [Christopher Hesse](https://twitter.com/christophrhesse)** <img src='imgs/edges2cats.jpg' width="400px"/> If you use this code for your research, please cite: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks.<br> [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/)\*, [Taesung Park](https://taesung.me/)\*, [Phillip Isola](https://people.eecs.berkeley.edu/~isola/), [Alexei A. Efros](https://people.eecs.berkeley.edu/~efros). In ICCV 2017. (\* equal contributions) [[Bibtex]](https://junyanz.github.io/CycleGAN/CycleGAN.txt) Image-to-Image Translation with Conditional Adversarial Networks.<br> [Phillip Isola](https://people.eecs.berkeley.edu/~isola), [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/), [Tinghui Zhou](https://people.eecs.berkeley.edu/~tinghuiz), [Alexei A. Efros](https://people.eecs.berkeley.edu/~efros). In CVPR 2017. [[Bibtex]](https://www.cs.cmu.edu/~junyanz/projects/pix2pix/pix2pix.bib) ## Talks and Course pix2pix slides: [keynote](http://efrosgans.eecs.berkeley.edu/CVPR18_slides/pix2pix.key) | [pdf](http://efrosgans.eecs.berkeley.edu/CVPR18_slides/pix2pix.pdf), CycleGAN slides: [pptx](http://efrosgans.eecs.berkeley.edu/CVPR18_slides/CycleGAN.pptx) | [pdf](http://efrosgans.eecs.berkeley.edu/CVPR18_slides/CycleGAN.pdf) CycleGAN course assignment [code](http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/assignments/a4-code.zip) and [handout](http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/assignments/a4-handout.pdf) designed by Prof. [Roger Grosse](http://www.cs.toronto.edu/~rgrosse/) for [CSC321](http://www.cs.toronto.edu/~rgrosse/courses/csc321_2018/) "Intro to Neural Networks and Machine Learning" at University of Toronto. Please contact the instructor if you would like to adopt it in your course. ## Colab Notebook TensorFlow Core CycleGAN Tutorial: [Google Colab](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/generative/cyclegan.ipynb) | [Code](https://github.com/tensorflow/docs/blob/master/site/en/tutorials/generative/cyclegan.ipynb) TensorFlow Core pix2pix Tutorial: [Google Colab](https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/generative/pix2pix.ipynb) | [Code](https://github.com/tensorflow/docs/blob/master/site/en/tutorials/generative/pix2pix.ipynb) PyTorch Colab notebook: [CycleGAN](https://colab.research.google.com/github/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/CycleGAN.ipynb) and [pix2pix](https://colab.research.google.com/github/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/pix2pix.ipynb) ZeroCostDL4Mic Colab notebook: [CycleGAN](https://colab.research.google.com/github/HenriquesLab/ZeroCostDL4Mic/blob/master/Colab_notebooks_Beta/CycleGAN_ZeroCostDL4Mic.ipynb) and [pix2pix](https://colab.research.google.com/github/HenriquesLab/ZeroCostDL4Mic/blob/master/Colab_notebooks_Beta/pix2pix_ZeroCostDL4Mic.ipynb) ## Other implementations ### CycleGAN <p><a href="https://github.com/leehomyc/cyclegan-1"> [Tensorflow]</a> (by Harry Yang), <a href="https://github.com/architrathore/CycleGAN/">[Tensorflow]</a> (by Archit Rathore), <a href="https://github.com/vanhuyz/CycleGAN-TensorFlow">[Tensorflow]</a> (by Van Huy), <a href="https://github.com/XHUJOY/CycleGAN-tensorflow">[Tensorflow]</a> (by Xiaowei Hu), <a href="https://github.com/LynnHo/CycleGAN-Tensorflow-2"> [Tensorflow2]</a> (by Zhenliang He), <a href="https://github.com/luoxier/CycleGAN_Tensorlayer"> [TensorLayer1.0]</a> (by luoxier), <a href="https://github.com/tensorlayer/cyclegan"> [TensorLayer2.0]</a> (by zsdonghao), <a href="https://github.com/Aixile/chainer-cyclegan">[Chainer]</a> (by Yanghua Jin), <a href="https://github.com/yunjey/mnist-svhn-transfer">[Minimal PyTorch]</a> (by yunjey), <a href="https://github.com/Ldpe2G/DeepLearningForFun/tree/master/Mxnet-Scala/CycleGAN">[Mxnet]</a> (by Ldpe2G), <a href="https://github.com/tjwei/GANotebooks">[lasagne/Keras]</a> (by tjwei), <a href="https://github.com/simontomaskarlsson/CycleGAN-Keras">[Keras]</a> (by Simon Karlsson), <a href="https://github.com/Ldpe2G/DeepLearningForFun/tree/master/Oneflow-Python/CycleGAN">[OneFlow]</a> (by Ldpe2G) </p> </ul> ### pix2pix <p><a href="https://github.com/affinelayer/pix2pix-tensorflow"> [Tensorflow]</a> (by Christopher Hesse), <a href="https://github.com/Eyyub/tensorflow-pix2pix">[Tensorflow]</a> (by Eyyüb Sariu), <a href="https://github.com/datitran/face2face-demo"> [Tensorflow (face2face)]</a> (by Dat Tran), <a href="https://github.com/awjuliani/Pix2Pix-Film"> [Tensorflow (film)]</a> (by Arthur Juliani), <a href="https://github.com/kaonashi-tyc/zi2zi">[Tensorflow (zi2zi)]</a> (by Yuchen Tian), <a href="https://github.com/pfnet-research/chainer-pix2pix">[Chainer]</a> (by mattya), <a href="https://github.com/tjwei/GANotebooks">[tf/torch/keras/lasagne]</a> (by tjwei), <a href="https://github.com/taey16/pix2pixBEGAN.pytorch">[Pytorch]</a> (by taey16) </p> </ul> ## Prerequisites - Linux or macOS - Python 3 - CPU or NVIDIA GPU + CUDA CuDNN ## Getting Started ### Installation - Clone this repo: ```bash git clone https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix cd pytorch-CycleGAN-and-pix2pix ``` - Install [PyTorch](http://pytorch.org) and other dependencies. For Conda users, you can create a new Conda environment by ```bash conda env create -f environment.yml ``` and then activate the environment by ```bash conda activate pytorch-img2img ``` - For Docker users, we provide the pre-built Docker image and Dockerfile. Please refer to our [Docker](docs/docker.md) page. - For Repl users, please click [![Run on Repl.it](https://repl.it/badge/github/junyanz/pytorch-CycleGAN-and-pix2pix)](https://repl.it/github/junyanz/pytorch-CycleGAN-and-pix2pix). ### CycleGAN train/test - Download a CycleGAN dataset (e.g. maps): ```bash bash ./datasets/download_cyclegan_dataset.sh maps ``` - To log training progress and test images to W&B dashboard, set the `--use_wandb` flag with training script - Train a model: ```bash #!./scripts/train_cyclegan.sh python train.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan --use_wandb ``` To see more intermediate results, check out `./checkpoints/maps_cyclegan/web/index.html`. - Test the model: ```bash #!./scripts/test_cyclegan.sh python test.py --dataroot ./datasets/maps --name maps_cyclegan --model cycle_gan ``` - The test results will be saved to a html file here: `./results/maps_cyclegan/latest_test/index.html`. ### pix2pix train/test - Download a pix2pix dataset (e.g.[facades](http://cmp.felk.cvut.cz/~tylecr1/facade/)): ```bash bash ./datasets/download_pix2pix_dataset.sh facades ``` - To log training progress and test images to W&B dashboard, set the `--use_wandb` flag with training script - Train a model: ```bash #!./scripts/train_pix2pix.sh python train.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --direction BtoA --use_wandb ``` To see more intermediate results, check out `./checkpoints/facades_pix2pix/web/index.html`. - Test the model (`bash ./scripts/test_pix2pix.sh`): ```bash #!./scripts/test_pix2pix.sh python test.py --dataroot ./datasets/facades --name facades_pix2pix --model pix2pix --direction BtoA ``` - The test results will be saved to a html file here: `./results/facades_pix2pix/test_latest/index.html`. You can find more scripts at `scripts` directory. - To train and test pix2pix-based colorization models, please add `--model colorization` and `--dataset_mode colorization`. See our training [tips](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/tips.md#notes-on-colorization) for more details. ### Apply a pre-trained model (CycleGAN) - You can download a pretrained model (e.g. horse2zebra) with the following script: ```bash bash ./scripts/download_cyclegan_model.sh horse2zebra ``` - The pretrained model is saved at `./checkpoints/{name}_pretrained/latest_net_G.pth`. Check [here](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/scripts/download_cyclegan_model.sh#L3) for all the available CycleGAN models. - To test the model, you also need to download the horse2zebra dataset: ```bash bash ./datasets/download_cyclegan_dataset.sh horse2zebra ``` - Then generate the results using ```bash python test.py --dataroot datasets/horse2zebra/testA --name horse2zebra_pretrained --model test --no_dropout ``` - The option `--model test` is used for generating results of CycleGAN only for one side. This option will automatically set `--dataset_mode single`, which only loads the images from one set. On the contrary, using `--model cycle_gan` requires loading and generating results in both directions, which is sometimes unnecessary. The results will be saved at `./results/`. Use `--results_dir {directory_path_to_save_result}` to specify the results directory. - For pix2pix and your own models, you need to explicitly specify `--netG`, `--norm`, `--no_dropout` to match the generator architecture of the trained model. See this [FAQ](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/docs/qa.md#runtimeerror-errors-in-loading-state_dict-812-671461-296) for more details. ### Apply a pre-trained model (pix2pix) Download a pre-trained model with `./scripts/download_pix2pix_model.sh`. - Check [here](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/scripts/download_pix2pix_model.sh#L3) for all the available pix2pix models. For example, if you would like to download label2photo model on the Facades dataset, ```bash bash ./scripts/download_pix2pix_model.sh facades_label2photo ``` - Download the pix2pix facades datasets: ```bash bash ./datasets/download_pix2pix_dataset.sh facades ``` - Then generate the results using ```bash python test.py --dataroot ./datasets/facades/ --direction BtoA --model pix2pix --name facades_label2photo_pretrained ``` - Note that we specified `--direction BtoA` as Facades dataset's A to B direction is photos to labels. - If you would like to apply a pre-trained model to a collection of input images (rather than image pairs), please use `--model test` option. See `./scripts/test_single.sh` for how to apply a model to Facade label maps (stored in the directory `facades/testB`). - See a list of currently available models at `./scripts/download_pix2pix_model.sh` ### Multi-GPU training To train a model on multiple GPUs, please use `torchrun --nproc_per_node=4 train.py ...` instead of `python train.py ...`. We also need to use synchronized batchnorm by setting `--norm sync_batch` (or `--norm sync_instance` for instance normgalization). The `--norm batch` is not compatible with DDP. ## [Docker](docs/docker.md) We provide the pre-built Docker image and Dockerfile that can run this code repo. See [docker](docs/docker.md). ## [Datasets](docs/datasets.md) Download pix2pix/CycleGAN datasets and create your own datasets. ## [Training/Test Tips](docs/tips.md) Best practice for training and testing your models. ## [Frequently Asked Questions](docs/qa.md) Before you post a new question, please first look at the above Q & A and existing GitHub issues. ## Custom Model and Dataset If you plan to implement custom models and dataset for your new applications, we provide a dataset [template](data/template_dataset.py) and a model [template](models/template_model.py) as a starting point. ## [Code structure](docs/overview.md) To help users better understand and use our code, we briefly overview the functionality and implementation of each package and each module. ## Pull Request You are always welcome to contribute to this repository by sending a [pull request](https://help.github.com/articles/about-pull-requests/). Please run `flake8 --ignore E501 .` and `pytest scripts/test_before_push.py -v` before you commit the code. Please also update the code structure [overview](docs/overview.md) accordingly if you add or remove files. ## Citation If you use this code for your research, please cite our papers. ``` @inproceedings{CycleGAN2017, title={Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks}, author={Zhu, Jun-Yan and Park, Taesung and Isola, Phillip and Efros, Alexei A}, booktitle={Computer Vision (ICCV), 2017 IEEE International Conference on}, year={2017} } @inproceedings{isola2017image, title={Image-to-Image Translation with Conditional Adversarial Networks}, author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on}, year={2017} } ``` ## Other Languages [Spanish](docs/README_es.md) ## Related Projects [img2img-turbo](https://github.com/GaParmar/img2img-turbo)<br> [contrastive-unpaired-translation](https://github.com/taesungp/contrastive-unpaired-translation) (CUT)<br> [CycleGAN-Torch](https://github.com/junyanz/CycleGAN) | [pix2pix-Torch](https://github.com/phillipi/pix2pix) | [pix2pixHD](https://github.com/NVIDIA/pix2pixHD)| [BicycleGAN](https://github.com/junyanz/BicycleGAN) | [vid2vid](https://tcwang0509.github.io/vid2vid/) | [SPADE/GauGAN](https://github.com/NVlabs/SPADE)<br> [iGAN](https://github.com/junyanz/iGAN) | [GAN Dissection](https://github.com/CSAILVision/GANDissect) | [GAN Paint](http://ganpaint.io/) ## Cat Paper Collection If you love cats, and love reading cool graphics, vision, and learning papers, please check out the Cat Paper [Collection](https://github.com/junyanz/CatPapers). ## Acknowledgments Our code is inspired by [pytorch-DCGAN](https://github.com/pytorch/examples/tree/master/dcgan).

ML Frameworks Image Editing

25.1K Github Stars

Open Source

iGAN

Interactive Image Generation via Generative Adversarial Networks

LLM Tools & Chat UIs

4K Github Stars

Open Source

interactive-deep-colorization

# Interactive Deep Colorization [Project Page](https://richzhang.github.io/InteractiveColorization) | [Paper](https://arxiv.org/abs/1705.02999) | [Demo Video](https://youtu.be/eL5ilZgM89Q) | [SIGGRAPH Talk](https://www.youtube.com/watch?v=rp5LUSbdsys) <img src='imgs/demo.gif' width=600> <b>04/10/2020 Update</b>: [@mabdelhack](mabdelhack) provided a windows installation guide for the PyTorch model in Python 3.6. Check out the Windows [branch](https://github.com/junyanz/interactive-deep-colorization/tree/windows) for the guide. <b>10/3/2019 Update</b>: Our technology is also now available in Adobe Photoshop Elements 2020. See this [blog](https://helpx.adobe.com/photoshop-elements/using/colorize-photo.html) and [video](https://www.youtube.com/watch?v=tmXg4N4YlJg) for more details. <b>9/3/2018 Update</b>: The code now supports a backend PyTorch model (with PyTorch 0.5.0+). Please find the Local Hints Network training code in the [colorization-pytorch](https://github.com/richzhang/colorization-pytorch) repository. Real-Time User-Guided Image Colorization with Learned Deep Priors. [Richard Zhang](https://richzhang.github.io/)\*, [Jun-Yan Zhu](https://www.cs.cmu.edu/~junyanz/)\*, [Phillip Isola](http://people.eecs.berkeley.edu/~isola/), [Xinyang Geng](http://young-geng.xyz/), Angela S. Lin, Tianhe Yu, and [Alexei A. Efros](https://people.eecs.berkeley.edu/~efros/). In ACM Transactions on Graphics (SIGGRAPH 2017). (\*indicates equal contribution) We first describe the system <b>(0) Prerequisities</b> and steps for <b>(1) Getting started</b>. We then describe the interactive colorization demo <b>(2) Interactive Colorization (Local Hints Network)</b>. There are two demos: (a) a "barebones" version in iPython notebook and (b) the full GUI we used in our paper. We then provide an example of the <b>(3) Global Hints Network</b>. <img src='https://richzhang.github.io/InteractiveColorization/index_files/imagenet_showcase_small.jpg' width=800> ### (0) Prerequisites - Linux or OSX - [Caffe](http://caffe.berkeleyvision.org/installation.html) or PyTorch - CPU or NVIDIA GPU + CUDA CuDNN. ### (1) Getting Started - Clone this repo: ```bash git clone https://github.com/junyanz/interactive-deep-colorization ideepcolor cd ideepcolor ``` - Download the reference model ``` bash ./models/fetch_models.sh ``` - Install [Caffe](http://caffe.berkeleyvision.org/installation.html) or [PyTorch]() and 3rd party Python libraries ([OpenCV](http://opencv.org/), [scikit-learn](http://scikit-learn.org/stable/install.html) and [scikit-image](https://github.com/scikit-image/scikit-image)). See the [Requirements](#Requirements) for more details. ### (2) Interactive Colorization (Local Hints Network) <img src='imgs/teaser_v3.jpg' width=800> We provide a "barebones" demo in iPython notebook, which does not require QT. We also provide our full GUI demo. #### (2a) Barebones Interactive Colorization Demo - Run `ipython notebook` and click on [`DemoInteractiveColorization.ipynb`](./DemoInteractiveColorization.ipynb). If you need to convert the Notebook to an older version, use `jupyter nbconvert --to notebook --nbformat 3 ./DemoInteractiveColorization.ipynb`. #### (2b) Full Demo GUI - Install [Qt5](https://doc.qt.io/qt-5/gettingstarted.html) and [QDarkStyle](https://github.com/ColinDuquesnoy/QDarkStyleSheet). (See [Installation](https://github.com/junyanz/interactive-deep-colorization#installation)) - Run the UI: `python ideepcolor.py --gpu [GPU_ID] --backend [CAFFE OR PYTORCH]`. Arguments are described below: ``` --win_size [512] GUI window size --gpu [0] GPU number --image_file ['./test_imgs/mortar_pestle.jpg'] path to the image file --backend ['caffe'] either use 'caffe' or 'pytorch'; 'caffe' is the official model from siggraph 2017, and 'pytorch' is the same weights converted ``` - User interactions <img src='./imgs/pad.jpg' width=800> - <b>Adding points</b>: Left-click somewhere on the input pad - <b>Moving points</b>: Left-click and hold on a point on the input pad, drag to desired location, and let go - <b>Changing colors</b>: For currently selected point, choose a recommended color (middle-left) or choose a color on the ab color gamut (top-left) - <b>Removing points</b>: Right-click on a point on the input pad - <b>Changing patch size</b>: Mouse wheel changes the patch size from 1x1 to 9x9 - <b>Load image</b>: Click the load image button and choose desired image - <b>Restart</b>: Click on the restart button. All points on the pad will be removed. - <b>Save result</b>: Click on the save button. This will save the resulting colorization in a directory where the ```image_file``` was, along with the user input ab values. - <b>Quit</b>: Click on the quit button. ### (3) Global Hints Network <img src='https://richzhang.github.io/InteractiveColorization/index_files/lab_all_figures45k_small.jpg' width=800> We include an example usage of our Global Hints Network, applied to global histogram transfer. We show its usage in an iPython notebook. - Add `./caffe_files` to your `PYTHONPATH` - Run `ipython notebook`. Click on [`./DemoGlobalHistogramTransfer.ipynb`](./DemoGlobalHistogramTransfer.ipynb) ### Installation - Install Caffe or PyTorch. The Caffe model is official. PyTorch is a reimplementation. - Install Caffe: see the Caffe [installation](http://caffe.berkeleyvision.org/installation.html) and Ubuntu installation [document](http://caffe.berkeleyvision.org/install_apt.html). Please compile the Caffe with the python layer [support](https://chrischoy.github.io/research/caffe-python-layer/) (set `WITH_PYTHON_LAYER=1` in the `Makefile.config`) and build Caffe python library by `make pycaffe`. You also need to add `pycaffe` to your `PYTHONPATH`. Use `vi ~/.bashrc` to edit the environment variables. ```bash PYTHONPATH=/path/to/caffe/python:$PYTHONPATH LD_LIBRARY_PATH=/path/to/caffe/build/lib:$LD_LIBRARY_PATH ``` - Install PyTorch: see the PyTorch [installation](https://pytorch.org/) guide. - Install scikit-image, scikit-learn, opencv, Qt5, and QDarkStyle pacakges: ```bash # ./install/install_deps.sh sudo pip install scikit-image sudo pip install scikit-learn sudo apt-get install python-opencv sudo apt-get install qt5-default sudo pip install qdarkstyle ``` For Conda users, type the following command lines (this may work for full Anaconda but not Miniconda): ```bash # ./install/install_conda.sh conda install -c anaconda protobuf ## photobuf conda install -c anaconda scikit-learn=0.19.1 ## scikit-learn conda install -c anaconda scikit-image=0.13.0 ## scikit-image conda install -c menpo opencv=2.4.11 ## opencv conda install -c anaconda qt ## qt5 conda install -c auto qdarkstyle ## qdarkstyle ``` For Docker users, please follow the Docker [document](https://github.com/junyanz/interactive-deep-colorization/tree/master/docker). - **Docker**: [[OSX Docker file](https://hub.docker.com/r/vbisbest/ideepcolor_osx/)] and [[OSX Installation video](https://www.youtube.com/watch?v=IORcb4lQlxQ)] by @vbisbest, [[Docker file 2](https://hub.docker.com/r/swallner/ideepcolor/)] (by @sabrinawallner) based on [DL Docker](https://github.com/floydhub/dl-docker). - More installation [help](https://github.com/junyanz/interactive-deep-colorization/issues/10) (by @SleepProgger). ### Training Please find a PyTorch reimplementation of the Local Hints Network training code in the [colorization-pytorch](https://github.com/richzhang/colorization-pytorch) repository. ### Citation If you use this code for your research, please cite our paper: ``` @article{zhang2017real, title={Real-Time User-Guided Image Colorization with Learned Deep Priors}, author={Zhang, Richard and Zhu, Jun-Yan and Isola, Phillip and Geng, Xinyang and Lin, Angela S and Yu, Tianhe and Efros, Alexei A}, journal={ACM Transactions on Graphics (TOG)}, volume={9}, number={4}, year={2017}, publisher={ACM} } ``` ### Cat Paper Collection One of the authors objects to the inclusion of this list, due to an allergy. Another author objects on the basis that cats are silly creatures and this is a serious, scientific paper. However, if you love cats, and love reading cool graphics, vision, and learning papers, please check out the Cat Paper Collection: [[Github]](https://github.com/junyanz/CatPapers) [[Webpage]](https://www.cs.cmu.edu/~junyanz/cat/cat_papers.html)

ML Frameworks Image Editing

2.7K Github Stars

Open Source

CatPapers

## Cat Paper Collection As reported by Cisco, 90% of net traffic will be visual, and indeed, most of the visual data are cat photos and videos. Thus, understanding, modeling, and synthesizing our feline friends becomes a more and more critical research problem these days, especially for our cat lovers. **Cat Paper Collection** is an academic paper collection that includes computer graphics, computer vision, and machine learning papers that produce experimental results related to **cats**. If you want to add/remove an article, please send an email to [Jun-Yan Zhu](https://github.com/junyanz/) (junyanz at cs dot cmu dot edu). We thank all the authors for their contribution and support. See also [Webpage](http://www.cs.cmu.edu/~junyanz/cat/cat_papers.html) | [CSV file](https://github.com/junyanz/CatPapers/blob/master/data/reference.csv) <br> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2601.00090"><img src="teasers/Harrington2025.jpg"/></a></td> <td align="left" width=550>Its Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models<br> <a href="https://anneharrington.github.io/">Anne Harrington</a>, <a href="https://akoepke.github.io/">A. Sophia Koepke</a>, <a href="https://sgk98.github.io/">Shyamgopal Karthik</a>, <a href="https://people.eecs.berkeley.edu/~trevor/">Trevor Darrell</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In arXiv 2025<br> <a href="https://arxiv.org/abs/2601.00090">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://sihyun.me/REPA/"><img src="teasers/Yu2025.jpg"/></a></td> <td align="left" width=550>Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think<br> <a href="https://sihyun.me/">Sihyun Yu</a>, <a href="https://sang-kyung.github.io/">Sangkyung Kwak</a>, <a href="https://huiwon-jang.github.io/">Huiwon Jang</a>, <a href="https://jh-jeong.github.io/">Jongheon Jeong</a>, <a href="http://jonathan-huang.org/">Jonathan Huang</a>, <a href="https://alinlab.kaist.ac.kr/shin.html">Jinwoo Shin</a>, <a href="https://www.sainingxie.com/">Saining Xie</a><br> In ICLR 2025<br> <a href="http://arxiv.org/abs/2410.06940">[Paper]</a> <a href="https://sihyun.me/REPA/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://compvis.github.io/mask/"><img src="teasers/Hu2024b.jpg"/></a></td> <td align="left" width=550>MASK is All You Need<br> <a href="https://taohu.me/">Vincent Tao Hu</a>, <a href="https://ommer-lab.com/people/ommer/">Bj&#246rn Ommer</a><br> In arXiv 2024<br> <a href="https://arxiv.org/abs/2412.06787">[Paper]</a> <a href="https://compvis.github.io/mask/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://taohu.me/zigma/"><img src="teasers/Hu2024.jpg"/></a></td> <td align="left" width=550>ZIGMA: A DiT-style Zigzag Mamba Diffusion Model<br> <a href="https://taohu.me/">Vincent Tao Hu</a>, <a href="https://stefan-baumann.eu/">Stefan Andreas Baumann</a>, <a href="https://www.linkedin.com/in/ming-gui-87b76a16b/?originalSubdomain=de">Ming Gui</a>, <a href="https://www.linkedin.com/in/grebenkovao/">Olga Grebenkova</a>, <a href="https://www.linkedin.com/in/pingchuan-ma-492543156/">Pingchuan Ma</a>, <a href="https://www.linkedin.com/in/js-fischer/">Johannes Fischer</a>, <a href="https://ommer-lab.com/people/ommer/">Bj&#246rn Ommer</a><br> In ECCV 2024<br> <a href="https://arxiv.org/abs/2403.13802">[Paper]</a> <a href="https://taohu.me/zigma/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2311.17048"><img src="teasers/Han2024.jpg"/></a></td> <td align="left" width=550>Zero-shot Referring Expression Comprehension via Structural Similarity Between Images and Captions<br> <a href="https://show-han.github.io/">Zeyu Han</a>, <a href="https://fangruizhu.github.io/">Fangrui Zhu</a>, <a href="https://estherbear.github.io/">Qianru Lao</a>, <a href="https://jianghz.me/">Huaizu Jiang</a><br> In CVPR 2024<br> <a href="https://arxiv.org/abs/2311.17048">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2211.09324"><img src="teasers/Choi2023.jpg"/></a></td> <td align="left" width=550>Blurring-Sharpening Process Models for Collaborative Filtering<br> <a href="https://jeongwhanchoi.me/">Jeongwhan Choi</a>, <a href="https://seoyoungh.github.io">Seoyoung Hong</a>, <a href="https://scholar.google.com/citations?user=VSuM3gYAAAAJ&hl=en">Noseong Park</a>, <a href="https://scholar.google.com/citations?user=px5LGgMAAAAJ&hl=en">Sung-Bae Cho</a><br> In SIGIR 2023<br> <a href="https://arxiv.org/abs/2211.09324">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2304.12152"><img src="teasers/Jiang2023.jpg"/></a></td> <td align="left" width=550>Efficient Halftoning via Deep Reinforcement Learning<br> Haitian Jiang, Dongliang Xiong, Xiaowen Jiang, Li Ding, Liang Chen, Kai Huang<br> In IEEE TIP 2023<br> <a href="https://arxiv.org/abs/2304.12152">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2203.08140"><img src="teasers/Xiang2022.jpg"/></a></td> <td align="left" width=550>Learning Spatio-Temporal Downsampling for Effective Video Upscaling<br> <a href="https://engineering.purdue.edu/people/xiaoyu.xiang.1">Xiaoyu Xiang</a>, <a href="https://yapengtian.org/">Yapeng Tian</a>, <a href="https://apvijay.github.io/">Vijay Rengarajan</a>, Lucas Young, <a href="https://scholar.google.com/citations?user=GwGsvm0AAAAJ&hl=en">Bo Zhu</a>, Rakesh Ranjan<br> In ECCV 2022<br> <a href="https://arxiv.org/abs/2203.08140">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://banmo-www.github.io/"><img src="teasers/Yang2022.jpg"/></a></td> <td align="left" width=550>BANMo: Building Animatable 3D Neural Models from Many Casual Videos<br> <a href="https://gengshan-y.github.io/">Gengshan Yang</a>, <a href="https://minhpvo.github.io/">Minh Vo</a>, <a href="https://nneverova.github.io/">Natalia Neverova</a>, <a href="http://www.cs.cmu.edu/~deva/">Deva Ramanan</a>, <a href="https://www.robots.ox.ac.uk/~vedaldi/">Andrea Vedaldi</a>, <a href="https://jhugestar.github.io/">Hanbyul Joo</a><br> In CVPR 2022<br> <a href="https://arxiv.org/abs/2112.12761">[Paper]</a> <a href="https://banmo-www.github.io/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/2203.14863"><img src="teasers/Xiang2022b.jpg"/></a></td> <td align="left" width=550>HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars<br> <a href="https://engineering.purdue.edu/people/xiaoyu.xiang.1">Xiaoyu Xiang</a>, Jon Morton, <a href="https://fitsumreda.github.io/">Fitsum A Reda</a>, Lucas Young, <a href="https://fperazzi.github.io/">Federico Perazzi</a>, Rakesh Ranjan, Amit Kumar, Andrea Colaco, Jan Allebach<br> In ArXiv 2022<br> <a href="https://arxiv.org/abs/2203.14863">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://chengao.vision/FGVC/"><img src="teasers/Gao2020.jpg"/></a></td> <td align="left" width=550>Flow-edge Guided Video Completion<br> <a href="http://chengao.vision/">Chen Gao</a>, Ayush Saraf, <a href="https://filebox.ece.vt.edu/~jbhuang/">Jia-Bin Huang</a>, <a href="https://johanneskopf.de/">Johannes Kopf</a><br> In ECCV 2020<br> <a href="https://arxiv.org/pdf/2009.01835.pdf">[Paper]</a> <a href="http://chengao.vision/FGVC/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://kaiyuyue.com/mgd/"><img src="teasers/Yue2020.jpg"/></a></td> <td align="left" width=550>Matching Guided Distillation<br> <a href="https://kaiyuyue.com/">Kaiyu Yue</a>, Jiangfan Deng, <a href="http://www.f-zhou.com/">Feng Zhou</a><br> In ECCV 2020<br> <a href="https://arxiv.org/pdf/2008.09958.pdf">[Paper]</a> <a href="http://kaiyuyue.com/mgd/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://ieeexplore.ieee.org/document/8703138"><img src="teasers/Yan2019.jpg"/></a></td> <td align="left" width=550>Strong 3D Printing by TPMS Injection<br> Xin Yan, Cong Rao, Lin Lu, <a href="https://www.cs.bgu.ac.il/~asharf/">Andrei Sharf</a>, <a href="http://irc.cs.sdu.edu.cn/~zhaohaisen/">Haisen Zhao</a>, <a href="https://cfcs.pku.edu.cn/baoquan/">Baoquan Chen</a><br> In IEEE TVCG 2019<br> <a href="https://ieeexplore.ieee.org/document/8703138">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://cvil.eecs.yorku.ca/projects/public_html/wb_emulation/index.html"><img src="teasers/Afifi2019.jpg"/></a></td> <td align="left" width=550>What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance<br> <a href="https://sites.google.com/view/mafifi">Mahmoud Afifi</a>, <a href="http://www.cse.yorku.ca/~mbrown/">Michael S Brown</a><br> In ICCV 2019<br> <a href="https://arxiv.org/pdf/1912.06960.pdf">[Paper]</a> <a href="http://cvil.eecs.yorku.ca/projects/public_html/wb_emulation/index.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/NVlabs/stylegan"><img src="teasers/Karras2019.jpg"/></a></td> <td align="left" width=550>A Style-Based Generator Architecture for Generative Adversarial Networks<br> <a href="https://research.nvidia.com/person/tero-karras">Tero Karras</a>, <a href="https://users.aalto.fi/~laines9/">Samuli Laine</a>, <a href="https://research.nvidia.com/person/timo-aila">Timo Aila</a><br> In CVPR 2019<br> <a href="https://arxiv.org/abs/1812.04948">[Paper]</a> <a href="https://github.com/NVlabs/stylegan">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/AlexiaJM/RelativisticGAN"><img src="teasers/Jolicoeur-Martineau2018.jpg"/></a></td> <td align="left" width=550>The relativistic discriminator: a key element missing from standard GAN<br> <a href="https://ajolicoeur.wordpress.com/">Alexia Jolicoeur-Martineau</a><br> In arXiv 2018<br> <a href="https://arxiv.org/pdf/1807.00734.pdf">[Paper]</a> <a href="https://github.com/AlexiaJM/RelativisticGAN">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://irc.cs.sdu.edu.cn/DSCarver/"><img src="teasers/Zhao2018.jpg"/></a></td> <td align="left" width=550>DSCarver: Decompose-and-Spiral-Carve for Subtractive Manufacturing<br> <a href="http://irc.cs.sdu.edu.cn/~zhaohaisen/">Haisen Zhao</a>, <a href="http://www.cs.sfu.ca/~haoz/">Hao Zhang</a>, <a href="https://sites.google.com/site/xinshiqing/">Shiqing Xin</a>, Yuanmin Deng, Changhe Tu, <a href="https://i.cs.hku.hk/~wenping/">Wenping Wang</a>, <a href="http://www.cs.tau.ac.il/~dcor/">Daniel Cohen-Or</a>, <a href="http://www.cs.sdu.edu.cn/~baoquan/">Baoquan Chen</a><br> In SIGGRAPH 2018<br> <a href="http://irc.cs.sdu.edu.cn/DSCarver/files/DSCarver.pdf">[Paper]</a> <a href="http://irc.cs.sdu.edu.cn/DSCarver/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://fve.bfa.edu.cn/recap/nbbs/"><img src="teasers/Aberman2018.jpg"/></a></td> <td align="left" width=550>Neural Best-Buddies: Sparse Cross-Domain Correspondence<br> <a href="https://kfiraberman.github.io/">Kfir Aberman</a>, <a href="https://liaojing.github.io/html/">Jing Liao</a>, <a href="https://rubbly.cn/">Mingyi Shi</a>, <a href="http://www.cs.huji.ac.il/~danix/">Dani Lischinski</a>, <a href="http://www.cs.sdu.edu.cn/~baoquan/">Baoquan Chen</a>, <a href="https://www.cs.tau.ac.il/~dcor/">Daniel Cohen-Or</a><br> In SIGGRAPH 2018<br> <a href="https://arxiv.org/abs/1805.04140">[Paper]</a> <a href="http://fve.bfa.edu.cn/recap/nbbs/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://people.csail.mit.edu/jsolomon/assets/curve_fmaps.pdf"><img src="teasers/Gehre2018.jpg"/></a></td> <td align="left" width=550>Interactive Curve Constrained Functional Maps<br> <a href="https://www.graphics.rwth-aachen.de/person/33/">Anne Gehre</a>, <a href="https://www.radcliffe.harvard.edu/people/michael-bronstein">Michael Bronstein</a>, <a href="https://www.graphics.rwth-aachen.de/person/3/">Leif Kobbelt</a>, <a href="http://people.csail.mit.edu/jsolomon/">Justin Solomon</a><br> In SGP 2018<br> <a href="https://people.csail.mit.edu/jsolomon/assets/curve_fmaps.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/pdf/1802.08195"><img src="teasers/Elsayed2018.jpg"/></a></td> <td align="left" width=550>Adversarial Examples that Fool both Computer Vision and Time-Limited Humans<br> <a href="https://ai.google/research/people/GamaleldinFathyElsayed">Gamaleldin F. Elsayed</a>, <a href="shreya-shankar.com">Shreya Shankar</a>, <a href="https://scholar.google.com/citations?user=7N-ethYAAAAJ&hl=en">Brian Cheung</a>, <a href="https://www.papernot.fr/">Nicolas Papernot</a>, <a href="https://ai.google/research/people/AlexeyKurakin">Alex Kurakin</a>, <a href="https://www.iangoodfellow.com/">Ian Goodfellow</a>, <a href="http://www.sohldickstein.com/">Jascha Sohl-Dickstein</a><br> In NeurIPS 2018<br> <a href="https://arxiv.org/pdf/1802.08195">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/1704.03477"><img src="teasers/Ha2018.jpg"/></a></td> <td align="left" width=550>A Neural Representation of Sketch Drawings<br> <a href="https://research.google.com/pubs/105004.html">David Ha</a>, <a href="https://research.google.com/pubs/author39086.html">Douglas Eck</a><br> In ICLR 2018<br> <a href="https://arxiv.org/abs/1704.03477">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/brownvc/ganimorph/"><img src="teasers/Gokaslan2018.jpg"/></a></td> <td align="left" width=550>Improving Shape Deformation in Unsupervised Image-to-Image Translation<br> <a href="https://skylion007.github.io/">Aaron Gokaslan</a>, <a href="http://vivekr.me/">Vivek Ramanujan</a>, <a href="https://dritchie.github.io/">Daniel Ritchie</a>, <a href="https://researchportal.bath.ac.uk/en/persons/kwang-in-kim/">Kwang In Kim</a>, <a href="http://jamestompkin.com/">James Tompkin</a><br> In ECCV 2018<br> <a href="https://arxiv.org/pdf/1808.04325.pdf">[Paper]</a> <a href="https://github.com/brownvc/ganimorph/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/NVlabs/MUNIT"><img src="teasers/Huang2018.jpg"/></a></td> <td align="left" width=550>Multimodal UNsupervised Image-to-image Translation<br> <a href="http://www.cs.cornell.edu/~xhuang/">Xun Huang</a>, <a href="http://mingyuliu.net/">Ming-Yu Liu</a>, <a href="https://vision.cornell.edu/se3/people/serge-belongie/">Serge Belongie</a>, <a href="http://jankautz.com/">Jan Kautz</a><br> In ECCV 2018<br> <a href="https://arxiv.org/pdf/1804.04732.pdf">[Paper]</a> <a href="https://github.com/NVlabs/MUNIT">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://ps.is.tuebingen.mpg.de/publications/zuffi-cvpr-2018"><img src="teasers/Zuffi2018.jpg"/></a></td> <td align="left" width=550>Lions and Tigers and Bears: Capturing Non-Rigid 3D Articulated Shape from Images<br> <a href="https://ps.is.tuebingen.mpg.de/person/szuffi">Silvia Zuffi</a>, <a href="https://people.eecs.berkeley.edu/~kanazawa/">Angjoo Kanazawa</a>, <a href="https://ps.is.mpg.de/~black">Michael J. Black</a><br> In CVPR 2018<br> <a href="http://files.is.tue.mpg.de/black/papers/zuffiCVPR2018.pdf">[Paper]</a> <a href="https://ps.is.tuebingen.mpg.de/publications/zuffi-cvpr-2018">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://people.eecs.berkeley.edu/~lingqi/publications/paper_fur2.pdf"><img src="teasers/Yan2017.jpg"/></a></td> <td align="left" width=550>An Efficient and Practical Near and Far Field Fur Reflectance Model<br> <a href="https://people.eecs.berkeley.edu/~lingqi/">Ling-Qi Yan</a>, <a href="graphics.ucsd.edu/~henrik/">Henrik Wann Jensen</a>, <a href="http://cseweb.ucsd.edu/~ravir/">Ravi Ramamoorthi</a><br> In SIGGRAPH 2017<br> <a href="https://people.eecs.berkeley.edu/~lingqi/publications/paper_fur2.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/"><img src="teasers/Wang2017.jpg"/></a></td> <td align="left" width=550>Light Field Video Capture Using a Learning-Based Hybrid Imaging System<br> <a href="https://people.eecs.berkeley.edu/~tcwang0509/">Ting-Chun Wang</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="http://nkhademi.com/">Nima Khademi Kalantari</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a>, <a href="http://cseweb.ucsd.edu/~ravir/">Ravi Ramamoorthi</a><br> In SIGGRAPH 2017<br> <a href="https://arxiv.org/abs/1705.02997">[Paper]</a> <a href="http://cseweb.ucsd.edu/~viscomp/projects/LF/papers/SIG17/lfv/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/mingyuliutw/UNIT"><img src="teasers/Liu2017.jpg"/></a></td> <td align="left" width=550>Unsupervised Image-to-Image Translation Networks<br> <a href="http://mingyuliu.net/">Ming-Yu Liu</a>, <a href="http://www.iupr.com/tmb">Thomas Breuel</a>, <a href="http://jankautz.com/">Jan Kautz</a><br> In NIPS 2017<br> <a href="https://arxiv.org/pdf/1703.00848.pdf">[Paper]</a> <a href="https://github.com/mingyuliutw/UNIT">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://junyanz.github.io/CycleGAN/"><img src="teasers/Zhu*2017.jpg"/></a></td> <td align="left" width=550>Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks<br> <a href="http://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu*</a>, <a href="https://taesung.me/">Taesung Park*</a>, <a href="http://people.eecs.berkeley.edu/~isola/">Phillip Isola</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In ICCV 2017<br> <a href="https://arxiv.org/abs/1703.10593">[Paper]</a> <a href="https://junyanz.github.io/CycleGAN/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/1705.02193"><img src="teasers/Thewlis2017.jpg"/></a></td> <td align="left" width=550>Unsupervised learning of object landmarks by factorized spatial embeddings<br> <a href="http://www.robots.ox.ac.uk/~jdt/">James Thewlis</a>, <a href="http://homepages.inf.ed.ac.uk/hbilen/">Hakan Bilen</a>, <a href="http://www.robots.ox.ac.uk/~vedaldi/">Andrea Vedaldi</a><br> In ICCV 2017<br> <a href="https://arxiv.org/abs/1705.02193">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/phillipi/pix2pix"><img src="teasers/Isola2017.jpg"/></a></td> <td align="left" width=550>Image-to-Image Translation with Conditional Adversarial Networks<br> <a href="https://github.com/phillipi">Phillip Isola</a>, <a href="https://www.cs.cmu.edu/~junyanz/">Jun-Yan Zhu</a>, <a href="https://people.eecs.berkeley.edu/~tinghuiz/">Tinghui Zhou</a>, <a href="https://people.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In CVPR 2017<br> <a href="https://arxiv.org/abs/1611.07004">[Paper]</a> <a href="https://github.com/phillipi/pix2pix">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/abs/1612.06370"><img src="teasers/Pathak2017.jpg"/></a></td> <td align="left" width=550>Learning Features by Watching Objects Move<br> <a href="https://people.eecs.berkeley.edu/~pathak/">Deepak Pathak</a>, <a href="http://www.rossgirshick.info/">Ross Girshick</a>, <a href="https://pdollar.github.io/">Piotr Dollar</a>, <a href="https://people.eecs.berkeley.edu/~trevor/">Trevor Darrell</a>, <a href="http://home.bharathh.info/">Bharath Hariharan</a><br> In CVPR 2017<br> <a href="https://arxiv.org/abs/1612.06370">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://jeremywrnr.com/project/codepilot/"><img src="teasers/Warner2017.jpg"/></a></td> <td align="left" width=550>CodePilot: Scaffolding End-to-End Collaborative Software Development for Novice Programmers<br> <a href="https://jeremywrnr.com/">Jeremy Warner</a>, <a href="http://www.pgbovine.net/index.html">Philip J. Guo</a><br> In CHI 2017<br> <a href="http://www.pgbovine.net/publications/CodePilot-collaborative-programming-IDE_CHI-2017.pdf">[Paper]</a> <a href="https://jeremywrnr.com/project/codepilot/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://joe.cat/CHI-revolt/"><img src="teasers/Chang2017.jpg"/></a></td> <td align="left" width=550>Revolt: Collaborative Crowdsourcing for Labeling Machine Learning Datasets<br> <a href="https://joe.cat/">Joseph Chee Chang</a>, <a href="http://saleemaamershi.com/">Saleema Amershi</a>, <a href="https://www.ecekamar.com/">Ece Kamar</a><br> In CHI 2017<br> <a href="https://joe.cat/images/papers/revolt-crowd-labeling.pdf">[Paper]</a> <a href="https://joe.cat/CHI-revolt/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://www.graphics.rwth-aachen.de/media/papers/Campen2016_SimplicialFoliations.pdf"><img src="teasers/Campen2016.jpg"/></a></td> <td align="left" width=550>Bijective Maps from Simplicial Foliations<br> <a href="https://www.graphics.rwth-aachen.de/person/7/">Marcel Campen</a>, <a href="http://vgc.poly.edu/~csilva/">Claudio T. Silva</a>, <a href="http://mrl.nyu.edu/~dzorin/">Denis Zorin</a><br> In SIGGRAPH 2016<br> <a href="https://www.graphics.rwth-aachen.de/media/papers/Campen2016_SimplicialFoliations.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://github.com/akanazawa/catdeform"><img src="teasers/Kanazawa2016.jpg"/></a></td> <td align="left" width=550>Learning 3D Deformation of Animals from 2D Images<br> <a href="http://www.umiacs.umd.edu/~kanazawa/">Angjoo Kanazawa</a>, <a href="https://services.math.duke.edu/~shaharko/">Shahar Kovalsky</a>, <a href="http://www.wisdom.weizmann.ac.il/~/ronen/">Ronen Basri</a>, <a href="https://www.cs.umd.edu/~djacobs/">David W. Jacobs</a><br> In Eurographics 2016<br> <a href="https://arxiv.org/abs/1507.07646">[Paper]</a> <a href="https://github.com/akanazawa/catdeform">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://arxiv.org/pdf/1608.04366.pdf"><img src="teasers/Wu2016.jpg"/></a></td> <td align="left" width=550>Infill Optimization for Additive Manufacturing--Approaching Bone-like Porous Structures<br> <a href="https://wwwcg.in.tum.de/group/persons/wu.html">Jun Wu</a>, <a href="http://www.dtu.dk/english/service/phonebook/person?id=18078&tab=2&qt=dtupublicationquery">Niels Aage</a>, <a href="https://wwwcg.in.tum.de/group/persons/westermann.html">R&#252diger Westermann</a>, <a href="http://www.dtu.dk/english/service/phonebook/person?id=2278&tab=1">Ole Sigmund</a><br> In Arxiv 2016<br> <a href="https://arxiv.org/pdf/1608.04366.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.eecs.berkeley.edu/~lingqi/publications/paper_fur.pdf"><img src="teasers/Yan2015.jpg"/></a></td> <td align="left" width=550>Physically-Accurate Fur Reflectance: Modeling, Measurement and Rendering<br> <a href="http://people.eecs.berkeley.edu/~lingqi/">Ling-Qi Yan</a>, <a href="http://cseweb.ucsd.edu/~c5tseng/">Chi-Wei Tseng</a>, <a href="graphics.ucsd.edu/~henrik/">Henrik Wann Jensen</a>, <a href="https://cseweb.ucsd.edu/~ravir/">Ravi Ramamoorthi</a><br> In SIGGRAPH Asia 2015<br> <a href="http://people.eecs.berkeley.edu/~lingqi/publications/paper_fur.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://members.loria.fr/JDumas/publications/sfsyn/"><img src="teasers/Dumas2015.jpg"/></a></td> <td align="left" width=550>By-Example Synthesis of Structurally Sound Patterns<br> <a href="https://members.loria.fr/JDumas/">J&#233r&#233mie Dumas</a>, An Lu, <a href="http://www.antexel.com/sylefeb/research">Sylvain Lefebvre</a>, <a href="https://wwwcg.in.tum.de/group/persons/wu.html">Jun Wu</a>, <a href="https://wwwcg.in.tum.de/group/persons/dick.html">Christian Dick</a><br> In SIGGRAPH 2015<br> <a href="https://members.loria.fr/JDumas/files/papers/sfsyn/byexsyn.pdf">[Paper]</a> <a href="https://members.loria.fr/JDumas/publications/sfsyn/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.columbia.edu/cg/hydrographics/"><img src="teasers/Zhang2015.jpg"/></a></td> <td align="left" width=550>Computational Hydrographic Printing<br> Yizhong Zhang, Chunji Yin, <a href="http://www.cs.columbia.edu/~cxz/">Changxi Zheng</a>, <a href="http://www.kunzhou.net/">Kun Zhou</a><br> In SIGGRAPH 2015<br> <a href="http://www.cs.columbia.edu/cg/hydrographics/hydrographics.pdf">[Paper]</a> <a href="http://www.cs.columbia.edu/cg/hydrographics/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.csail.mit.edu/jsolomon/assets/convolutional_w2.compressed.pdf"><img src="teasers/Solomon2015.jpg"/></a></td> <td align="left" width=550>Convolutional Wasserstein Distances: Efficient Optimal Transportation on Geometric Domains<br> <a href="http://people.csail.mit.edu/jsolomon/">Justin Solomon</a>, <a href="http://fernandodegoes.org/">Fernando de Goes</a>, <a href="http://gpeyre.github.io/"> Gabriel Peyre</a>, <a href="http://www.iip.ist.i.kyoto-u.ac.jp/member/cuturi/">Marco Cuturi</a>, <a href="http://autodeskresearch.com/people/adrianbutscher">Adrian Butscher</a>, Andy Nguyen, Tao Du, <a href="http://geometry.stanford.edu/member/guibas/">Leonidas Guibas</a><br> In SIGGRAPH 2015<br> <a href="http://people.csail.mit.edu/jsolomon/assets/convolutional_w2.compressed.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://wwwcg.in.tum.de/research/research/publications/2015/high-resolution-topology-optimization.html"><img src="teasers/Wu2015.jpg"/></a></td> <td align="left" width=550>A System for High-Resolution Topology Optimization<br> <a href="https://wwwcg.in.tum.de/group/persons/wu.html">Jun Wu</a>, <a href="https://wwwcg.in.tum.de/group/persons/dick.html">Christian Dick</a>, <a href="https://wwwcg.in.tum.de/group/persons/westermann.html">R&#252diger Westermann</a><br> In IEEE Transactions on Visualization and Computer Graphics 2015<br> <a href="http://wwwcg.in.tum.de/fileadmin/user_upload/Lehrstuehle/Lehrstuhl_XV/Research/Publications/2015/TopOpt/preprint.pdf">[Paper]</a> <a href="http://wwwcg.in.tum.de/research/research/publications/2015/high-resolution-topology-optimization.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.cs.cmu.edu/projects/deepContext/"><img src="teasers/Doersch2015.jpg"/></a></td> <td align="left" width=550>Unsupervised Visual Representation Learning by Context Prediction<br> <a href="http://www.cs.cmu.edu/~cdoersch/">Carl Doersch</a>, <a href="http://www.cs.cmu.edu/~abhinavg/">Abhinav Gupta</a>, <a href="http://www.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In ICCV 2015<br> <a href="http://arxiv.org/pdf/1505.05192v2">[Paper]</a> <a href="http://graphics.cs.cmu.edu/projects/deepContext/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf"><img src="teasers/Long2015.jpg"/></a></td> <td align="left" width=550>Fully Convolutional Networks for Semantic Segmentation<br> <a href="http://people.eecs.berkeley.edu/~jonlong/">Jon Long</a>, <a href="http://imaginarynumber.net/">Evan Shelhamer</a>, <a href="http://people.eecs.berkeley.edu/~trevor/">Trevor Darrell</a><br> In CVPR 2015<br> <a href="http://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://visual.cs.ucl.ac.uk/pubs/ccca/"><img src="teasers/Turmukhambetov2015.jpg"/></a></td> <td align="left" width=550>Modeling Object Appearance using Context-Conditioned Component Analysis<br> <a href="http://www.cs.ucl.ac.uk/staff/dturmukh/">Daniyar Turmukhambetov</a>, <a href="http://cs.bath.ac.uk/~nc537/">Neill D.F. Campbell</a>, <a href="http://www.cs.ucl.ac.uk/staff/s.prince/">Simon J.D. Prince</a>, <a href="http://www.cs.ucl.ac.uk/staff/s.prince/">Jan Kautz</a><br> In CVPR 2015<br> <a href="https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Turmukhambetov_Modeling_Object_Appearance_2015_CVPR_paper.pdf">[Paper]</a> <a href="http://visual.cs.ucl.ac.uk/pubs/ccca/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://arturodeza.github.io/virality/"><img src="teasers/Deza2015.jpg"/></a></td> <td align="left" width=550>Understanding Image Virality<br> <a href="http://arturodeza.wikidot.com/">Arturo Deza</a>, <a href="https://filebox.ece.vt.edu/~parikh/">Devi Parikh</a><br> In CVPR 2015<br> <a href="https://arxiv.org/abs/1503.02318">[Paper]</a> <a href="http://arturodeza.github.io/virality/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://sites.google.com/site/marcolivesu/quadlayouts"><img src="teasers/Usai2015.jpg"/></a></td> <td align="left" width=550>Extraction of the Quad Layout of a Triangle Mesh Guided by its Curve-Skeleton<br> <a href="http://francescousai.info/">Francesco Usai</a>, <a href="https://sites.google.com/site/marcolivesu/">Marco Livesu</a>, <a href="http://www.disi.unige.it/person/PuppoE/">Enrico Puppo</a>, <a href="http://vcg.isti.cnr.it/~tarini/">Marco Tarini</a>, <a href="http://ugo.sc.unica.it/">Riccardo Scateni</a><br> In ACM Transactions on Graphics (TOG) 2015<br> <a href="https://drive.google.com/open?id=0B6EEjMMaU7haZG9hVVpxSjd2dEE">[Paper]</a> <a href="https://sites.google.com/site/marcolivesu/quadlayouts">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://research.microsoft.com/en-us/um/people/hoppe/proj/morph/"><img src="teasers/Liao2014.jpg"/></a></td> <td align="left" width=550>Automating Image Morphing using Structural Similarity on a Halfway Domain<br> Jing Liao, <a href="http://www.rodlima.net/">Rodolfo Lima</a>, <a href="http://w3.impa.br/~diego/">Diego Nehab</a>, <a href="http://research.microsoft.com/en-us/um/people/hoppe/">Hugues Hoppe</a>, <a href="http://www.cse.ust.hk/~psander/">Pedro Sander</a>, <a href="http://www.cad.zju.edu.cn/home/jhyu/English.htm">Jinhui Yu</a><br> In SIGGRAPH 2014<br> <a href="http://www.cs.ust.hk/~psander/docs/pixmorph.pdf">[Paper]</a> <a href="http://research.microsoft.com/en-us/um/people/hoppe/proj/morph/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://www.cs.cmu.edu/~junyanz/projects/averageExplorer/index.html"><img src="teasers/Zhu2014.jpg"/></a></td> <td align="left" width=550>AverageExplorer: Interactive Exploration and Alignment of Visual Data Collections<br> <a href="https://www.cs.cmu.edu/~junyanz">Jun-Yan Zhu</a>, <a href="http://www.cs.ucdavis.edu/~yjlee/">Yong Jae Lee</a>, <a href="http://www.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In SIGGRAPH 2014<br> <a href="https://www.cs.cmu.edu/~junyanz/projects/averageExplorer/averageExplorer.pdf">[Paper]</a> <a href="https://www.cs.cmu.edu/~junyanz/projects/averageExplorer/index.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://sites.google.com/site/build2last43dp/"><img src="teasers/Lu2014.jpg"/></a></td> <td align="left" width=550>Build-to-Last: Strength to Weight 3D Printed Objects<br> <a href="http://vr.sdu.edu.cn/~lulin/">Lin Lu</a>, <a href="http://www.cs.bgu.ac.il/~asharf/">Andrei Sharf</a>, <a href="http://irc.cs.sdu.edu.cn/~zhaohaisen/">Haisen Zhao</a>, Yuan Wei, Qingnan Fan, Xuelin Chen, <a href="http://www.animlife.com/">Yann Savoye</a>, <a href="http://www.cs.sdu.edu.cn/zh/60">Changhe Tu</a>, <a href="http://www.cs.tau.ac.il/~dcor/">Daniel Cohen-Or</a>, <a href="http://www.cs.sdu.edu.cn/~baoquan/">Baoquan Chen</a><br> In SIGGRAPH 2014<br> <a href="https://www.cs.tau.ac.il/~dcor/articles/2014/Build-to-Last.pdf">[Paper]</a> <a href="https://sites.google.com/site/build2last43dp/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://sites.google.com/site/jbhuang0604/publications/struct_completion"><img src="teasers/Huang2014.jpg"/></a></td> <td align="left" width=550>Image Completion using Planar Structure Guidance<br> <a href="https://sites.google.com/site/jbhuang0604/">Jia-Bin Huang</a>, <a href="http://research.microsoft.com/en-us/people/sbkang/">Sing Bing Kang</a>, <a href="http://www.ece.illinois.edu/directory/profile.asp?n-ahuja">Narendra Ahuja</a>, <a href="http://johanneskopf.de/">Johannes Kopf</a><br> In SIGGRAPH 2014<br> <a href="https://www.box.com/shared/static/x3zb7p2qp696dxu3wf34.pdf">[Paper]</a> <a href="https://sites.google.com/site/jbhuang0604/publications/struct_completion">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.cs.uh.edu/ble/papers/2014s-ske/"><img src="teasers/Le2014.jpg"/></a></td> <td align="left" width=550>Robust and Accurate Skeletal Rigging from Mesh Sequences<br> <a href="http://graphics.cs.uh.edu/ble/about.php">Binh Huy Le</a>, <a href="http://graphics.cs.uh.edu/zdeng/">Zhigang Deng</a><br> In SIGGRAPH 2014<br> <a href="http://graphics.cs.uh.edu/ble/papers/2014s-ske/skeleton-draft.pdf">[Paper]</a> <a href="http://graphics.cs.uh.edu/ble/papers/2014s-ske/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.cs.cmu.edu/projects/contextPrediction/"><img src="teasers/Doersch2014.jpg"/></a></td> <td align="left" width=550>Context as Supervisory Signal: Discovering Objects with Predictable Context<br> <a href="http://www.cs.cmu.edu/~cdoersch/">Carl Doersch</a>, <a href="http://www.cs.cmu.edu/~abhinavg/">Abhinav Gupta</a>, <a href="http://www.eecs.berkeley.edu/~efros/">Alexei A. Efros</a><br> In ECCV 2014<br> <a href="http://graphics.cs.cmu.edu/projects/contextPrediction/contextPrediction.pdf">[Paper]</a> <a href="http://graphics.cs.cmu.edu/projects/contextPrediction/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/halftone_QR/halftoneQR_sigga13.html"><img src="teasers/Chu2013.jpg"/></a></td> <td align="left" width=550>Halftone QR Codes<br> <a href="http://cgv.cs.nthu.edu.tw/hkchu">Hung-Kuo Chu</a>, Chia-Sheng Chang, <a href="http://www.cs.nthu.edu.tw/~rrlee/rrlee/Home.html">Ruen-Rone Lee</a>, <a href="http://www0.cs.ucl.ac.uk/staff/n.mitra/">Niloy J. Mitra</a><br> In SIGGRAPH Asia 2013<br> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/halftone_QR/paper_docs/halftoneQR_sigga13.pdf">[Paper]</a> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/halftone_QR/halftoneQR_sigga13.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://graphics.ethz.ch/publications/papers/paperLuk13.php"><img src="teasers/Lukac2013.jpg"/></a></td> <td align="left" width=550>Painting by feature: texture boundaries for example-based image creation<br> <a href="http://dcgi.fel.cvut.cz/people/lukacmi1">Michal Lukac</a>, <a href="http://dcgi.fel.cvut.cz/people/fiserja9">Jakub Fiser</a>, <a href="https://graphics.ethz.ch/~jebazin/">Jean-Charles Bazin</a>, <a href="http://dcgi.fel.cvut.cz/people/jamriond">Ondrej Jamriska</a>, <a href="http://www.ahornung.net/">Alexander Sorkine-Hornung</a>, <a href="http://dcgi.felk.cvut.cz/home/sykorad/">Daniel Sykora</a><br> In SIGGRAPH 2013<br> <a href="https://s3-us-west-1.amazonaws.com/disneyresearch/wp-content/uploads/20150324052134/Painting-by-Feature-Paper.pdf">[Paper]</a> <a href="https://graphics.ethz.ch/publications/papers/paperLuk13.php">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://igl.ethz.ch/projects/winding-number"><img src="teasers/Jacobson2013.jpg"/></a></td> <td align="left" width=550>Robust Inside-Outside Segmentation using Generalized Winding Numbers<br> <a href="http://www.cs.columbia.edu/~jacobson/">Alec Jacobson</a>, <a href="http://www.seas.upenn.edu/~ladislav/">Ladislav Kavan</a>, <a href="http://igl.ethz.ch/people/sorkine/">Olga Sorkine-Hornung</a><br> In SIGGRAPH 2013<br> <a href="http://igl.ethz.ch/projects/winding-number/robust-inside-outside-segmentation-using-generalized-winding-numbers-siggraph-2013-jacobson-et-al.pdf">[Paper]</a> <a href="http://igl.ethz.ch/projects/winding-number">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.oneweirdkerneltrick.com/catbasis.pdf"><img src="teasers/Caturana2013.jpg"/></a></td> <td align="left" width=550>Cat Basis Purrsuit<br> <a href="http://dimatura.net/">Daniel Caturana</a>, <a href="http://www.cs.cmu.edu/~dfouhey/">David Furry</a><br> In SIGBOVIK 2013<br> <a href="http://www.oneweirdkerneltrick.com/catbasis.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.berkeley.edu/~barron/KarschCVPR2013.pdf"><img src="teasers/Karsch2013.jpg"/></a></td> <td align="left" width=550>Boundary Cues for 3D Object Shape Recovery<br> <a href="http://kevinkarsch.com/">Kevin Karsch</a>, <a href="http://web.engr.illinois.edu/~liao17/">Zicheng Liao</a>, Jason Rock, <a href="http://www.cs.berkeley.edu/~barron/">Jonathan T. Barron</a>, <a href="http://web.engr.illinois.edu/~dhoiem/">Derek Hoiem</a><br> In CVPR 2013<br> <a href="http://www.cs.berkeley.edu/~barron/KarschCVPR2013.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/nr_mesh/nrMesh_tog.html"><img src="teasers/Huang2013.jpg"/></a></td> <td align="left" width=550>Near-Regular Structure Discovery Using Linear Programming<br> <a href="http://ttic.uchicago.edu/~huangqx/">Qixing Huang</a>, <a href="http://geometry.stanford.edu/member/guibas/">Leonidas Guibas</a>, <a href="http://www0.cs.ucl.ac.uk/staff/n.mitra/">Niloy J. Mitra</a><br> In ACM Transactions on Graphics 2013<br> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/nr_mesh/paper_docs/nrMesh_tog.pdf">[Paper]</a> <a href="http://vecg.cs.ucl.ac.uk/Projects/SmartGeometry/nr_mesh/nrMesh_tog.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://hal.inria.fr/hal-00732992"><img src="teasers/Boye2012.jpg"/></a></td> <td align="left" width=550>A Vectorial Solver for Free-form Vector Gradients<br> <a href="http://manao.inria.fr/team/boye/">Simon Boye</a>, <a href="http://www.labri.fr/perso/barla/blog/">Pascal Barla</a>, <a href="http://www.labri.fr/perso/guenneba/">Gael Guennebaud</a><br> In SIGGRAPH Asia 2012<br> <a href="https://hal.archives-ouvertes.fr/hal-00732992/PDF/vs4vg_2012.pdf">[Paper]</a> <a href="https://hal.inria.fr/hal-00732992">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.sfu.ca/~pingtan/Papers/sigasia12.pdf"><img src="teasers/Chen2012.jpg"/></a></td> <td align="left" width=550>Manifold Preserving Edit Propagation<br> <a href="http://arts.buaa.edu.cn/staff/chen/index.htm">Xiaowu Chen</a>, Dongqing Zou, Qinping Zhao, <a href="http://www.cs.sfu.ca/~pingtan/">Ping Tan</a><br> In SIGGRAPH Asia 2012<br> <a href="http://www.cs.sfu.ca/~pingtan/Papers/sigasia12.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.717.3850&rep=rep1&type=pdf"><img src="teasers/Ovsjanikov2012.jpg"/></a></td> <td align="left" width=550>Functional Maps: A Flexible Representation of Maps Between Shapes<br> <a href="http://www.lix.polytechnique.fr/~maks/">Maks Ovsjanikov</a>, <a href="http://mirela.net.technion.ac.il/">Mirela Ben-Chen</a>, <a href="http://people.csail.mit.edu/jsolomon/">Justin Solomon</a>, <a href="https://autodeskresearch.com/people/adrian-butscher">Adrian Butscher</a>, <a href="http://geometry.stanford.edu/member/guibas/">Leonidas Guibas</a><br> In SIGGRAPH 2012<br> <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.717.3850&rep=rep1&type=pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://research.google.com/archive/unsupervised_icml2012.html"><img src="teasers/Le2012.jpg"/></a></td> <td align="left" width=550>Building High-level Features Using Large Scale Unsupervised Learning<br> <a href="http://cs.stanford.edu/~quocle/">Quoc Le</a>, <a href="http://www.cs.toronto.edu/~ranzato/">MarcAurelio Ranzato</a>, <a href="http://research.google.com/pubs/RajatMonga.html">Rajat Monga</a>, Matthieu Devin, Kai Chen, <a href="http://research.google.com/pubs/GregCorrado.html">Greg Corrado</a>, <a href="http://research.google.com/people/jeff/">Jeff Dean</a>, <a href="http://cs.stanford.edu/people/ang/">Andrew Ng</a><br> In ICML 2012<br> <a href="http://static.googleusercontent.com/media/research.google.com/en/us/archive/unsupervised_icml2012.pdf">[Paper]</a> <a href="http://research.google.com/archive/unsupervised_icml2012.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2012/parkhi12a/"><img src="teasers/Parkhi2012.jpg"/></a></td> <td align="left" width=550>Cats and Dogs<br> <a href="http://www.robots.ox.ac.uk/~vgg/publications/index.php?idAuthor=161">Omkar M Parkhi</a>, <a href="http://www.robots.ox.ac.uk/~vedaldi/">Andrea Vedaldi</a>, <a href="http://www.robots.ox.ac.uk/~az/">Andrew Zisserman</a>, <a href="http://www.iiit.ac.in/~jawahar/">C. V. Jawahar</a><br> In CVPR 2012<br> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2012/parkhi12a/parkhi12a.pdf">[Paper]</a> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2012/parkhi12a/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://web.engr.illinois.edu/~dhoiem/publications/cvpr2012_objectsegmentation_qieyun.pdf"><img src="teasers/Dai2012.jpg"/></a></td> <td align="left" width=550>Learning to Localize Detected Objects<br> <a href="http://web.engr.illinois.edu/~dai9/">Qieyun Dai</a>, <a href="http://web.engr.illinois.edu/~dhoiem/">Derek Hoiem</a><br> In CVPR 2012<br> <a href="http://web.engr.illinois.edu/~dhoiem/publications/cvpr2012_objectsegmentation_qieyun.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://sweb.cityu.edu.hk/hongbofu/projects/animatedconstructionoflinedrawings_sigga11/#.V3wdKZErI2w"><img src="teasers/Fu2011.jpg"/></a></td> <td align="left" width=550>Animated Construction of Line Drawings<br> <a href="http://sweb.cityu.edu.hk/hongbofu/">Hongbo Fu</a>, <a href="http://sweb.cityu.edu.hk/shizzhou/">Shizhe Zhou</a>, <a href="http://staff.ustc.edu.cn/~lgliu/"> Ligang Liu</a>, <a href="http://graphics.stanford.edu/~niloy/">Niloy J. Mitra</a><br> In SIGGRAPH Asia 2011<br> <a href="http://www.jdl.ac.cn/project/faceId/paperreading/Paper/nyji_20120329_2.pdf">[Paper]</a> <a href="http://sweb.cityu.edu.hk/hongbofu/projects/animatedconstructionoflinedrawings_sigga11/#.V3wdKZErI2w">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://www.microsoft.com/en-us/research/publication/nonlinear-revision-control-for-images/"><img src="teasers/Chen2011.jpg"/></a></td> <td align="left" width=550>Nonlinear Revision Control for Images<br> <a href="http://www.ht-timchen.com/">Hsiang-Ting Chen</a>, <a href="http://www.liyiwei.org/">Li-Yi Wei</a>, <a href="https://cchang.wordpress.com/\n">Chun-Fa Chang</a><br> In SIGGRAPH 2011<br> <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.465.986&rep=rep1&type=pdf">[Paper]</a> <a href="https://www.microsoft.com/en-us/research/publication/nonlinear-revision-control-for-images/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.princeton.edu/~funk/sig11.pdf"><img src="teasers/Kim2011.jpg"/></a></td> <td align="left" width=550>Blended Intrinsic Maps<br> <a href="http://vovakim.com/">Vladimir G. Kim</a>, <a href="http://www.wisdom.weizmann.ac.il/~ylipman/">Yaron Lipman</a>, <a href="http://www.cs.princeton.edu/~funk/"> Thomas Funkhouser</a><br> In SIGGRAPH 2011<br> <a href="http://www.cs.princeton.edu/~funk/sig11.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://zurich.disneyresearch.com/OverCoat/"><img src="teasers/Schmid2011.jpg"/></a></td> <td align="left" width=550>OverCoat: An Implicit Canvas for 3D Painting<br> Johannes Schmid, Martin Sebastian Senn, <a href="https://graphics.ethz.ch/people/grossm/">Markus Gross</a>, <a href="https://graphics.ethz.ch/~sumnerb/">Robert W. Sumner</a><br> In SIGGRAPH 2011<br> <a href="http://zurich.disneyresearch.com/OverCoat/OverCoat-preprint-s.pdf">[Paper]</a> <a href="http://zurich.disneyresearch.com/OverCoat/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.cmu.edu/~kmcrane/Projects/SpinTransformations/"><img src="teasers/Crane2011.jpg"/></a></td> <td align="left" width=550>Spin Transformations of Discrete Surfaces<br> <a href="http://www.cs.cmu.edu/~kmcrane/">Keenan Crane</a>, <a href="http://page.math.tu-berlin.de/~pinkall/">Ulrich Pinkall</a>, <a href="http://users.cms.caltech.edu/~ps/">Peter Schroder</a><br> In SIGGRAPH 2011<br> <a href="http://www.cs.cmu.edu/~kmcrane/Projects/SpinTransformations/paper.pdf">[Paper]</a> <a href="http://www.cs.cmu.edu/~kmcrane/Projects/SpinTransformations/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2011/Parkhi11/"><img src="teasers/Parkhi2011.jpg"/></a></td> <td align="left" width=550>The Truth About Cats and Dogs<br> <a href="http://www.robots.ox.ac.uk/~vgg/publications/index.php?idAuthor=161">Omkar M Parkhi</a>, <a href="http://www.robots.ox.ac.uk/~vedaldi/">Andrea Vedaldi</a>, <a href="http://www.iiit.ac.in/~jawahar/">C. V. Jawahar</a>, <a href="http://www.robots.ox.ac.uk/~az/">Andrew Zisserman</a><br> In ICCV 2011<br> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2011/Parkhi11/parkhi11.pdf">[Paper]</a> <a href="http://www.robots.ox.ac.uk/~vgg/publications/2011/Parkhi11/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://meekohi.com/Holroyd10/"><img src="teasers/Holroyd2010.jpg"/></a></td> <td align="left" width=550>A Coaxial Optical Scanner for Synchronous Acquisition of 3D Geometry and Surface Reflectance<br> <a href="http://meekohi.com/">Michael Holroyd</a>, <a href="http://www.cs.virginia.edu/~jdl/">Jason Lawrence</a>, <a href="http://www.eecs.harvard.edu/~zickler/">Todd Zickler</a><br> In SIGGRAPH 2010<br> <a href="http://www.cs.virginia.edu/~mjh7v/papers/Holroyd10.pdf">[Paper]</a> <a href="http://meekohi.com/Holroyd10/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://resources.mpi-inf.mpg.de/ResolutionEnhancement/"><img src="teasers/Didyk2010.jpg"/></a></td> <td align="left" width=550>Apparent Display Resolution Enhancement for Moving Images<br> <a href="http://people.csail.mit.edu/pdidyk/">Piotr Didyk</a>, <a href="http://perso.telecom-paristech.fr/~eisemann/">Elmar Eisemann</a>, <a href="http://www.mpi-inf.mpg.de/~ritschel/">Tobias Ritschel</a>, <a href="http://www.mpi-inf.mpg.de/~karol/">Karol Myszkowski</a>, <a href="http://www.mpi-inf.mpg.de/~hpseidel/">Hans-Peter Seidel</a><br> In SIGGRAPH 2010<br> <a href="http://resources.mpi-inf.mpg.de/ResolutionEnhancement/ResolutionEnhancement.pdf">[Paper]</a> <a href="http://resources.mpi-inf.mpg.de/ResolutionEnhancement/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.gmrv.es/Publications/2010/SPO10/"><img src="teasers/Schvartzman2010.jpg"/></a></td> <td align="left" width=550>Star-Contours for Efficient Hierarchical Self-Collision Detection<br> <a href="http://www.gmrv.es/~sschvartzman">Sara C. Schvartzman</a>, <a href="http://www.gmrv.es/~aperez/">Alvaro G. Perez</a>, <a href="http://www.gmrv.es/~motaduy">Miguel A. Otaduy</a><br> In SIGGRAPH 2010<br> <a href="http://www.gmrv.es/Publications/2010/SPO10/SCTT.pdf">[Paper]</a> <a href="http://www.gmrv.es/Publications/2010/SPO10/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://kaiminghe.com/eccv10/index.html"><img src="teasers/He2010.jpg"/></a></td> <td align="left" width=550>Guided Image Filtering<br> <a href="http://kaiminghe.com/">Kaiming He</a>, <a href="http://www.jiansun.org/">Jian Sun</a>, <a href="https://www.ie.cuhk.edu.hk/people/xotang.shtml">Xiaoou Tang</a><br> In ECCV 2010<br> <a href="http://kaiminghe.com/publications/eccv10guidedfilter.pdf">[Paper]</a> <a href="http://kaiminghe.com/eccv10/index.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://gfx.cs.princeton.edu/pubs/Lipman_2009_MVF/index.php"><img src="teasers/Lipman2009.jpg"/></a></td> <td align="left" width=550>Mobius Voting for Surface Correspondence<br> <a href="http://www.wisdom.weizmann.ac.il/~ylipman/">Yaron Lipman</a>, <a href="http://www.cs.princeton.edu/~funk/">Thomas Funkhouser</a><br> In SIGGRAPH 2009<br> <a href="http://gfx.cs.princeton.edu/pubs/Lipman_2009_MVF/mobius.pdf">[Paper]</a> <a href="http://gfx.cs.princeton.edu/pubs/Lipman_2009_MVF/index.php">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.csail.mit.edu/wojciech/MovingGradients/"><img src="teasers/Mahajan2009.jpg"/></a></td> <td align="left" width=550>Moving Gradients: A Path-Based Method for Plausible Image Interpolation<br> <a href="http://www.cs.columbia.edu/~dhruv/">Dhruv Mahajan</a>, <a href="https://sites.google.com/site/jonash123/">Fu-Chung Huang</a>, <a href="http://people.csail.mit.edu/wojciech/">Wojciech Matusik</a>, <a href="https://cseweb.ucsd.edu/~ravir/">Ravi Ramamoorthi</a>, <a href="http://www.cs.columbia.edu/~belhumeur/">Peter Belhumeur</a><br> In SIGGRAPH 2009<br> <a href="http://people.csail.mit.edu/wojciech/MovingGradients/MovingGradients.pdf">[Paper]</a> <a href="http://people.csail.mit.edu/wojciech/MovingGradients/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://web.media.mit.edu/~bandy/rgb/"><img src="teasers/Bando2008.jpg"/></a></td> <td align="left" width=550>Extracting Depth and Matte using a Color-Filtered Aperture<br> <a href="http://web.media.mit.edu/~bandy/">Yosuke Bando</a>, <a href="http://www.management.ntu.edu.tw/en/teachers/17">Bing-Yu Chen</a>, <a href="http://nishitalab.org/user/nis/">Tomoyuki Nishita</a><br> In SIGGRAPH Asia 2008<br> <a href="http://web.media.mit.edu/~bandy/rgb/SIGA08rgb.pdf">[Paper]</a> <a href="http://web.media.mit.edu/~bandy/rgb/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://chiakailiang.org/pap/"><img src="teasers/Liang2008.jpg"/></a></td> <td align="left" width=550>Programmable Aperture Photography: Multiplexed Light Field Acquisition<br> <a href="http://chiakailiang.org/">Chia-Kai Liang</a>, <a href="http://mpac.ee.ntu.edu.tw/~lth/">Tai-Hsu Lin</a>, Bing-Yi Wong, Chi Liu, <a href="http://www.ee.ntu.edu.tw/bio?id=60">Homer Chen</a><br> In SIGGRAPH 2008<br> <a href="http://chiakailiang.org/pap/pdf/sig08_preprint.pdf">[Paper]</a> <a href="http://chiakailiang.org/pap/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cse.cuhk.edu.hk/~ttwong/papers/structurehalftone/structurehalftone.html"><img src="teasers/Pang2008.jpg"/></a></td> <td align="left" width=550>Structure-Aware Halftoning<br> <a href="http://www.cihe.edu.hk/~wmpang/">Wai-Man Pang</a>, Yingge Qu, <a href="http://www.cse.cuhk.edu.hk/~ttwong/myself.html">Tien-Tsin Wong</a>, <a href="http://www.math.tau.ac.il/~dcor/">Daniel Cohen-Or</a>, <a href="http://www.cse.cuhk.edu.hk/~pheng/">Pheng-Ann Heng</a><br> In SIGGRAPH 2008<br> <a href="https://www.researchgate.net/profile/Wai-Man_Pang/publication/200018906_Structure-Aware_Halftoning/links/02e7e51de74ad05a1b000000.pdf">[Paper]</a> <a href="http://www.cse.cuhk.edu.hk/~ttwong/papers/structurehalftone/structurehalftone.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://cis.jhu.edu/publications/papers_in_database/GEMAN/Fleuret-Geman_Cats_07.pdf"><img src="teasers/Fleuret2008.jpg"/></a></td> <td align="left" width=550>Stationary Features and Cat Detection<br> <a href="https://www.idiap.ch/~fleuret/">Fran&ccedilois Fleuret</a>, <a href="http://www.cis.jhu.edu/people/faculty/geman/">Donald Geman</a><br> In JMLR 2008<br> <a href="http://cis.jhu.edu/publications/papers_in_database/GEMAN/Fleuret-Geman_Cats_07.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://137.189.35.203/WebUI/CatDatabase/catData.html"><img src="teasers/Zhang2008.jpg"/></a></td> <td align="left" width=550>Cat Head Detection - How to Effectively Exploit Shape and Texture Features<br> Weiwei Zhang, <a href="http://research.microsoft.com/en-us/people/jiansun/">Jian Sun</a>, <a href="http://www.ie.cuhk.edu.hk/people/xotang.shtml">Xiaoou Tang</a><br> In ECCV 2008<br> <a href="http://research.microsoft.com/pubs/80582/ECCV_CAT_PROC.pdf">[Paper]</a> <a href="http://137.189.35.203/WebUI/CatDatabase/catData.html">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www-evasion.imag.fr/Publications/2007/AHLD07/"><img src="teasers/Aujay2007.jpg"/></a></td> <td align="left" width=550>Harmonic Skeleton for Realistic Character Animation<br> <a href="http://gregoire.aujay.free.fr/news.php">Gregoire Aujay</a>, <a href="http://morpheo.inrialpes.fr/people/hetroy/">Franck Hetroy</a>, <a href="http://www.gipsa-lab.grenoble-inp.fr/~francis.lazarus/">Francis Lazarus</a>, Christine Depraz<br> In Symposium on Computer Animation 2007<br> <a href="http://www-evasion.imag.fr/Publications/2007/AHLD07/HarmonicSkeleton.pdf">[Paper]</a> <a href="http://www-evasion.imag.fr/Publications/2007/AHLD07/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.mit.edu/~ibaran/autorig/"><img src="teasers/Baran2007.jpg"/></a></td> <td align="left" width=550>Automatic rigging and animation of 3D characters<br> <a href="http://www.mit.edu/~ibaran/">Ilya Baran</a>, <a href="http://people.csail.mit.edu/jovan/">Jovan Popovic</a><br> In SIGGRAPH 2007<br> <a href="http://people.csail.mit.edu/ibaran/papers/2007-SIGGRAPH-Pinocchio.pdf">[Paper]</a> <a href="http://www.mit.edu/~ibaran/autorig/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=8E1AD9DB3F200954341D4C96A1F9C9E1?doi=10.1.1.152.7336&rep=rep1&type=pdf"><img src="teasers/Shi2007.jpg"/></a></td> <td align="left" width=550>Mesh Puppetry: Cascading Optimization of Mesh Deformation with Inverse Kinematics<br> <a href="https://sites.google.com/site/royitaqi/">Xiaohan Shi</a>, <a href="http://www.kunzhou.net/">Kun Zhou</a>, <a href="http://www.cse.msu.edu/~ytong/">Yiying Tong</a>, <a href="http://www.geometry.caltech.edu/~mathieu/">Mathieu Desbrun</a>, <a href="http://www.cad.zju.edu.cn/home/bao/">Hujun Bao</a>, <a href="https://www.microsoft.com/en-us/research/people/bainguo/">Baining Guo</a><br> In SIGGRAPH 2007<br> <a href="http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=8E1AD9DB3F200954341D4C96A1F9C9E1?doi=10.1.1.152.7336&rep=rep1&type=pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://cvcl.mit.edu/hybridimage/"><img src="teasers/Oliva2006.jpg"/></a></td> <td align="left" width=550>Hybrid Images<br> <a href="http://cvcl.mit.edu/">Aude Oliva</a>, <a href="http://web.mit.edu/torralba/www/">Antonio Torralba</a>, <a href="http://www.gla.ac.uk/researchinstitutes/neurosciencepsychology/staff/philippeschyns/">Philippe G. Schyns</a><br> In SIGGRAPH 2006<br> <a href="http://cvcl.mit.edu/hybridimage/hybrid/OlivaTorralb_Hybrid_Siggraph06.pdf">[Paper]</a> <a href="http://cvcl.mit.edu/hybridimage/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://holgerweb.net/PhD/Research/VideoAbstraction/"><img src="teasers/Winnemoller2006.jpg"/></a></td> <td align="left" width=550>Real-Time Video Abstraction<br> <a href="http://holgerweb.net/PhD/">Holger Winnemoller</a>, <a href="http://www.cs.northwestern.edu/~sco590/">Sven C. Olsen</a>, <a href="http://www.cs.northwestern.edu/~bgooch/Publications.html">Bruce Gooch</a><br> In SIGGRAPH 2006<br> <a href="http://www.heathershrewsbury.com/dreu2010/wp-content/uploads/2010/07/RealTimeVideoAbstraction.pdf">[Paper]</a> <a href="http://holgerweb.net/PhD/Research/VideoAbstraction/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.cs.illinois.edu/papers/ssq"><img src="teasers/Dong2006.jpg"/></a></td> <td align="left" width=550>Spectral Surface Quadrangulation<br> Shen Dong, <a href="http://faculty.engineering.ucdavis.edu/bremer/">Peer-Timo Bremer</a>, <a href="http://mgarland.org/">Michael Garland</a>, <a href="http://www.pascucci.org/">Valerio Pascucci</a>, <a href="http://graphics.cs.illinois.edu/~jch/">John C. Hart</a><br> In SIGGRAPH 2006<br> <a href="http://graphics.cs.illinois.edu/sites/default/files/ssq.pdf">[Paper]</a> <a href="http://graphics.cs.illinois.edu/papers/ssq">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.math.rutgers.edu/~mischaik/papers/vecflddesn.pdf"><img src="teasers/Zhang2006.jpg"/></a></td> <td align="left" width=550>Vector Field Design on Surfaces<br> <a href="http://web.engr.oregonstate.edu/~zhange/">Eugene Zhang</a>, <a href="https://www.math.rutgers.edu/~mischaik/">Konstantin Mischaikow</a>, <a href="http://www.cc.gatech.edu/~turk/">Greg Turk</a><br> In ACM Transactions on Graphics (TOG) 2006<br> <a href="http://www.math.rutgers.edu/~mischaik/papers/vecflddesn.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.cs.jhu.edu/~misha/Fall09/Kharevych06.pdf"><img src="teasers/Kharevych2006.jpg"/></a></td> <td align="left" width=550>Discrete conformal mappings via circle patterns<br> Liliya Kharevych, <a href="http://page.math.tu-berlin.de/~springb/">Boris Springborn</a>, <a href="http://users.cms.caltech.edu/~ps/">Peter Schroder</a><br> In ACM Transactions on Graphics 2006<br> <a href="http://www.cs.jhu.edu/~misha/Fall09/Kharevych06.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://www.microsoft.com/en-us/research/publication/large-mesh-deformation-using-the-volumetric-graph-laplacian/"><img src="teasers/Zhou2005.jpg"/></a></td> <td align="left" width=550>Large mesh deformation using the volumetric graph Laplacian<br> <a href="http://www.kunzhou.net/">Kun Zhou</a>, <a href="http://www.cad.zju.edu.cn/home/hj/index.xml">Jin Huang</a>, <a href="http://research.microsoft.com/en-us/um/people/johnsny/">John Snyder</a>, <a href="http://www.cad.zju.edu.cn/home/xgliu/">Xinguo Liu</a>, <a href="http://www.cad.zju.edu.cn/home/bao/">Hujun Bao</a>, <a href="https://www.microsoft.com/en-us/research/people/bainguo/">Baining Guo</a>, <a href="https://news.microsoft.com/exec/harry-shum/#sm.0000132byn4sagcq3zb3rckw1y2ny">Heung-Yeung Shum</a><br> In SIGGRAPH 2005<br> <a href="https://www.microsoft.com/en-us/research/publication/large-mesh-deformation-using-the-volumetric-graph-laplacian/">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://kunzhou.net/publications/texturemontage.pdf"><img src="teasers/Zhou2005b.jpg"/></a></td> <td align="left" width=550>TextureMontage: Seamless Texturing of Arbitrary Surfaces From Multiple Images<br> <a href="http://www.kunzhou.net/">Kun Zhou</a>, Xi Wang, <a href="http://www.cse.msu.edu/~ytong/">Yiying Tong</a>, <a href="http://www.geometry.caltech.edu/~mathieu/">Mathieu Desbrun</a>, <a href="https://www.microsoft.com/en-us/research/people/bainguo/">Baining Guo</a>, <a href="https://news.microsoft.com/exec/harry-shum/#sm.0000132byn4sagcq3zb3rckw1y2ny">Heung-Yeung Shum</a><br> In SIGGRAPH 2005<br> <a href="http://kunzhou.net/publications/texturemontage.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.csail.mit.edu/sumner/research/deftransfer/"><img src="teasers/Sumner2004.jpg"/></a></td> <td align="left" width=550>Deformation Transfer for Triangle Meshes<br> <a href="https://graphics.ethz.ch/~sumnerb/">Robert W. Sumner</a>, <a href="http://www.adobe.com/technology/people/seattle/jovan-popovic.html">Jovan Popovic</a><br> In SIGGRAPH 2004<br> <a href="http://people.csail.mit.edu/sumner/research/deftransfer/Sumner2004DTF.pdf">[Paper]</a> <a href="http://people.csail.mit.edu/sumner/research/deftransfer/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.cs.yale.edu/site/publications/stereological-techniques-solid-textures?destination=node%2F57"><img src="teasers/Jagnow2004.jpg"/></a></td> <td align="left" width=550>Stereological Techniques for Solid Textures<br> <a href="http://robjagnow.com/">Robert Jagnow</a>, <a href="http://graphics.cs.yale.edu/site/people/julie-dorsey">Julie Dorsey</a>, <a href="http://graphics.cs.yale.edu/site/people/holly-rushmeier/">Holly Rushmeier</a><br> In ACM Transactions on Graphics (TOG) 2004<br> <a href="http://graphics.cs.yale.edu/site/sites/files/Stereological%20Techniques.pdf">[Paper]</a> <a href="http://graphics.cs.yale.edu/site/publications/stereological-techniques-solid-textures?destination=node%2F57">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.csail.mit.edu/bmcutler/PROJECTS/SIGGRAPH02/"><img src="teasers/Cutler2002.jpg"/></a></td> <td align="left" width=550>A Procedural Approach to Authoring Solid Models<br> <a href="http://www.cs.rpi.edu/~cutler/">Barbara Cutler</a>, <a href="http://graphics.cs.yale.edu/site/people/julie-dorsey/">Julie Dorsey</a>, <a href="http://www.csbio.unc.edu/mcmillan/index.py">Leonard McMillan</a>, <a href="http://matthias-mueller-fischer.ch/">Matthias Mueller</a>, <a href="http://www.robjagnow.com/">Robert Jagnow</a><br> In SIGGRAPH 2002<br> <a href="http://people.csail.mit.edu/bmcutler/PROJECTS/SIGGRAPH02/papers_0040_final.pdf">[Paper]</a> <a href="http://people.csail.mit.edu/bmcutler/PROJECTS/SIGGRAPH02/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://dl.acm.org/citation.cfm?id=566602"><img src="teasers/Zhang2002.jpg"/></a></td> <td align="left" width=550>Feature-based light field morphing<br> Zhunping Zhang, Lifeng Wang, <a href="https://www.microsoft.com/en-us/research/people/bainguo/"> Baining Guo</a>, <a href="https://news.microsoft.com/exec/harry-shum/#sm.0000132byn4sagcq3zb3rckw1y2ny">Heung-Yeung Shum</a><br> In SIGGRAPH 2002<br> <a href="http://dl.acm.org/citation.cfm?id=566602">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://www.msr-waypoint.com/en-us/um/people/xtong/BTFSynthesis.pdf"><img src="teasers/Tong2002.jpg"/></a></td> <td align="left" width=550>Synthesis of Bidirectional Texture Functions on Arbitrary Surfaces<br> <a href="http://research.microsoft.com/en-us/um/people/xtong/xtong.html">Xin Tong</a>, Jingdan Zhang, <a href="http://staff.ustc.edu.cn/~lgliu/"> Ligang Liu</a>, Xi Wang, <a href="https://www.microsoft.com/en-us/research/people/bainguo/">Baining Guo</a>, <a href="https://news.microsoft.com/exec/harry-shum/#sm.0000132byn4sagcq3zb3rckw1y2ny"> Heung-Yeung Shum</a><br> In SIGGRAPH 2002<br> <a href="http://www.msr-waypoint.com/en-us/um/people/xtong/BTFSynthesis.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.101.2205&rep=rep1&type=pdf"><img src="teasers/Sheffer2002.jpg"/></a></td> <td align="left" width=550>Smoothing an Overlay Grid to Minimize Linear Distortion in Texture Mapping<br> <a href="http://www.cs.ubc.ca/~sheffa/">Alla Sheffer</a>, <a href="http://www.math.vt.edu/people/sturler/">Eric de Sturler</a><br> In ACM Transactions on Graphics (TOG) 2002<br> <a href="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.101.2205&rep=rep1&type=pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="https://graphics.stanford.edu/papers/invrend/"><img src="teasers/Ramamoorthi2001.jpg"/></a></td> <td align="left" width=550>A Signal-Processing Framework for Inverse Rendering<br> <a href="https://cseweb.ucsd.edu/~ravir/">Ravi Ramamoorthi</a>, <a href="https://graphics.stanford.edu/~hanrahan/">Pat Hanrahan</a><br> In SIGGRAPH 2001<br> <a href="https://graphics.stanford.edu/papers/invrend/invrend.pdf">[Paper]</a> <a href="https://graphics.stanford.edu/papers/invrend/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://people.csail.mit.edu/ericchan/bib/pdf/p227-lengyel.pdf"><img src="teasers/Lengyel2001.jpg"/></a></td> <td align="left" width=550>Real-Time Fur over Arbitrary Surfaces<br> Jerome E. Lengyel, <a href="http://www.cs.utah.edu/~emilp/">Emil Praun</a>, <a href="https://www.cs.princeton.edu/~af/">Adam Finkelstein</a>, <a href="http://research.microsoft.com/en-us/um/people/hoppe/">Hugues Hoppe</a><br> In SIGGRAPH 2001<br> <a href="http://people.csail.mit.edu/ericchan/bib/pdf/p227-lengyel.pdf">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://graphics.stanford.edu/papers/texture-synthesis-sig01/"><img src="teasers/Wei2001.jpg"/></a></td> <td align="left" width=550>Texture Synthesis over Arbitrary Manifold Surfaces<br> <a href="http://www.liyiwei.org/">Li-Yi Wei</a>, <a href="http://graphics.stanford.edu/~levoy/">Marc Levoy</a><br> In SIGGRAPH 2001<br> <a href="http://graphics.stanford.edu/papers/texture-synthesis-sig01/texture.pdf">[Paper]</a> <a href="http://graphics.stanford.edu/papers/texture-synthesis-sig01/">[Project]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://dl.acm.org/citation.cfm?id=151281"><img src="teasers/Geist1993.jpg"/></a></td> <td align="left" width=550>A Markovian framework for digital halftoning<br> <a href="https://people.cs.clemson.edu/~geist/homepage.html">Robert Geist</a>, Robert Reynolds, Darrell Suggs<br> In ACM Transactions on Graphics (TOG) 1993<br> <a href="http://dl.acm.org/citation.cfm?id=151281">[Paper]</a> </td></tr></tbody></table> <table> <tbody> <tr> <td align="left" width=250> <a href="http://web.mit.edu/persci/classes/papers/Attneave54.pdf"><img src="teasers/Attneave1954.jpg"/></a></td> <td align="left" width=550>Some informational aspects of visual perception<br> <a href="http://psycnet.apa.org/index.cfm?fa=buy.optionToBuy&id=1994-31267-001">Fred Attneave</a><br> In Psychological Review 1954<br> <a href="http://web.mit.edu/persci/classes/papers/Attneave54.pdf">[Paper]</a> </td></tr></tbody></table> <br> Last updated in Jan 2026 <br>

Education & Learning Note Taking

1.2K Github Stars