MagicArticulate: Make Your 3D Models Articulation-Ready

Chaoyue Song^1,2, Jianfeng Zhang^2*, Xiu Li², Fan Yang^1,2, Yiwen Chen¹, Zhongcong Xu², Jun Hao Liew², Xiaoyang Guo², Fayao Liu³, Jiashi Feng², Guosheng Lin^1*
*Corresponding authors
¹ Nanyang Technological University ² Bytedance Seed ³ A*STAR

CVPR 2025

Project | Paper | Code | Video

Update

• 2025.4.16: Release weights for skeleton generation trained on Articulation-XL2.0.

Overview

This repository includes weights of MagicArticulate trained on Articulation-XL2.0. These are the numbers that you should be able to reproduce using the released weights and the current version of the codebase:

Test set	Articulation-XL2.0-test			ModelResource-test
	CD-J2J	CD-J2B	CD-B2B	CD-J2J	CD-J2B	CD-B2B
Paper (train on 1.0, spatial)	-	-	-	4.103	3.101	2.672
Paper (train on 1.0, hier)	-	-	-	4.451	3.454	2.998
train on Arti-XL2.0 (spatial)	3.043	2.293	1.953	3.936	2.979	2.588
train on Arti-XL2.0 (hier)	3.417	2.692	2.281	4.116	3.124	2.704

The performance comparison between models trained on Articulation-XL1.0 versus 2.0 demonstrates the importance of dataset scaling with high quality. If you wish to compare your methods with MagicArticulate trained on Articulation-XL2.0, you may reference these results as a baseline for comparison.

Citation

@article{song2025magicarticulate,
      title={MagicArticulate: Make Your 3D Models Articulation-Ready}, 
      author={Chaoyue Song and Jianfeng Zhang and Xiu Li and Fan Yang and Yiwen Chen and Zhongcong Xu and Jun Hao Liew and Xiaoyang Guo and Fayao Liu and Jiashi Feng and Guosheng Lin},
      journal={arXiv preprint arXiv:2502.12135},
      year={2025},
}