manycore-research

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 manycore-research

Open Source

PlankAssembly

PlankAssembly is a research software presented at ICCV 2023 for robust 3D reconstruction from three orthographic views using learnt shape programs. Developed by researchers including Wentao Hu and Jia Zheng, the tool transforms engineering drawings into 3D geometric models by leveraging a program-based representation. The system supports multiple input configurations, including visible and hidden lines, visible edges only, and sidefaces, enabling flexible processing of technical diagrams. It is implemented in Python using PyTorch and PyTorch Lightning, with dependencies on PythonOCC for rendering and geometric operations. The software includes a dataset for training and testing, which can be rendered into three-view orthogonal drawings or processed as SVG and JSON files. Users can also explore variations such as raster image inputs or comparisons with PolyGen through dedicated repository branches. PlankAssembly is particularly useful for applications in computer vision, CAD automation, and 3D modeling where p

ML Frameworks 3D Modeling & Animation

102 Github Stars

Open Source

CAD2Program

CAD2Program is an advanced vision-language system presented at AAAI 2025 that automatically converts 2D CAD drawings into 3D parametric models. This software leverages state-of-the-art artificial intelligence to interpret complex engineering diagrams and reconstruct them as editable, dimensionally accurate 3D geometries. It is designed for engineers, architects, and researchers who need to streamline the transition from legacy 2D documentation to modern 3D workflows. The tool serves as a powerful research prototype demonstrating the capabilities of multimodal learning in computer-aided design. The project includes source code for its official research website, which is built using a template originally developed for the Nerfies project. The software and its associated documentation are released under the Creative Commons Attribution-ShareAlike 4.0 International License, allowing for broad usage, adaptation, and distribution provided that appropriate credit is given and any derivative works are shared under th

ML Frameworks 3D Modeling & Animation

23 Github Stars