|
|
--- |
|
|
pipeline_tag: image-to-3d |
|
|
license: gpl-3.0 |
|
|
--- |
|
|
|
|
|
# PrimitiveAnything |
|
|
|
|
|
<p align="center"> |
|
|
📃 <a href="https://arxiv.org/abs/2505.04622" target="_blank">Paper</a> • 💻 <a href="https://github.com/PrimitiveAnything/PrimitiveAnything" target="_blank">[Github Repo]</a> • 🌐 <a href="https://primitiveanything.github.io/" target="_blank">Project Page</a> |
|
|
</p> |
|
|
|
|
|
This repository contains the weights for the model presented in the paper [PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer](https://arxiv.org/abs/2505.04622). |
|
|
|
|
|
**PrimitiveAnything** is a novel framework to decompose complex shapes into 3D primitive assemblies via the auto-regressive transformer. |
|
|
|
|
|
## Citation |
|
|
|
|
|
If you find our work useful, please consider citing PrimitiveAnything: |
|
|
|
|
|
``` |
|
|
@article{ye2025primitiveanything, |
|
|
title={PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer}, |
|
|
author={Ye, Jingwen and He, Yuze and Zhou, Yanning and Zhu, Yiqin and Xiao, Kaiwen and Liu, Yong-Jin and Yang, Wei and Han, Xiao}, |
|
|
journal={arXiv preprint arXiv:2505.04622}, |
|
|
year={2025} |
|
|
} |
|
|
``` |
