ArtFormer: Controllable Generation of Diverse 3D Articulated Objects
Abstract
This paper presents a novel framework for modeling and conditional generation of 3D articulated objects. Troubled by flexibility-quality tradeoffs, existing methods are often limited to using predefined structures or retrieving shapes from static datasets. To address these challenges, we parameterize an articulated object as a tree of tokens and employ a transformer to generate both the object's high-level geometry code and its kinematic relations. Subsequently, each sub-part's geometry is further decoded using a signed-distance-function (SDF) shape prior, facilitating the synthesis of high-quality 3D shapes. Our approach enables the generation of diverse objects with high-quality geometry and varying number of parts. Comprehensive experiments on conditional generation from text descriptions demonstrate the effectiveness and flexibility of our method.
Cite
Text
Su et al. "ArtFormer: Controllable Generation of Diverse 3D Articulated Objects." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00183Markdown
[Su et al. "ArtFormer: Controllable Generation of Diverse 3D Articulated Objects." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/su2025cvpr-artformer/) doi:10.1109/CVPR52734.2025.00183BibTeX
@inproceedings{su2025cvpr-artformer,
title = {{ArtFormer: Controllable Generation of Diverse 3D Articulated Objects}},
author = {Su, Jiayi and Feng, Youhe and Li, Zheng and Song, Jinhua and He, Yangfan and Ren, Botao and Xu, Botian},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {1894-1904},
doi = {10.1109/CVPR52734.2025.00183},
url = {https://mlanthology.org/cvpr/2025/su2025cvpr-artformer/}
}