AutoPartGen: Autogressive 3D Part Generation and Discovery
Paper • 2507.13346 • Published
You need to agree to share your contact information to access this model
The information you provide will be collected, stored, processed and shared in accordance with the Meta Privacy Policy.
Log in or Sign Up to review the conditions and access this model content.
AutoPartGen: Autoregressive 3D Part Generation and Discovery
Meta AI Research; University of Oxford, VGG
Minghao Chen, Jianyuan Wang, Roman Shapovalov, Tom Monnier,
Hyunyoung Jung, Dilin Wang, Rakesh Ranjan,
Iro Laina, Andrea Vedaldi
NeurIPS 2025
This repository provides a reimplementation of AutoPartGen based on TripoSG components and released checkpoints, since the original internal model is subject to release constraints. Its results are expected to differ from, and may underperform, the original system reported in the paper.
Quick Start
Please refer to our GitHub Repo.
Citation
If you find our repository useful, please consider giving it a star ⭐ and citing our paper in your work:
@inproceedings{chen2025autopartgen,
title={AutoPartGen: Autoregressive 3D Part Generation and Discovery},
author={Chen, Minghao and Wang, Jianyuan and Shapovalov, Roman and Monnier, Tom and Jung, Hyunyoung and Wang, Dilin and Ranjan, Rakesh and Laina, Iro and Vedaldi, Andrea},
booktitle={Advances in Neural Information Processing Systems},
year={2025}
}
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support