Particulate: Feed-Forward 3D Object Articulation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Ruining, Yao, Yuxin, Zheng, Chuanxia, Rupprecht, Christian, Lasenby, Joan, Wu, Shangzhe, Vedaldi, Andrea
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911547728592896
author Li, Ruining
Yao, Yuxin
Zheng, Chuanxia
Rupprecht, Christian
Lasenby, Joan
Wu, Shangzhe
Vedaldi, Andrea
author_facet Li, Ruining
Yao, Yuxin
Zheng, Chuanxia
Rupprecht, Christian
Lasenby, Joan
Wu, Shangzhe
Vedaldi, Andrea
contents We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Particulate: Feed-Forward 3D Object Articulation
Li, Ruining
Yao, Yuxin
Zheng, Chuanxia
Rupprecht, Christian
Lasenby, Joan
Wu, Shangzhe
Vedaldi, Andrea
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
We introduce Particulate, a feed-forward model that, given a 3D mesh of an object, infers its articulations, including its 3D parts, their kinematic structure, and the motion constraints. The model is based on a transformer network, the Part Articulation Transformer, which predicts all these parameters for all joints. We train the network end-to-end on a diverse collection of articulated 3D assets from public datasets. During inference, Particulate maps the output of the network back to the input mesh, yielding a fully articulated 3D model in seconds, much faster than prior approaches that require per-object optimization. Particulate also works on AI-generated 3D assets, enabling the generation of articulated 3D objects from a single (real or synthetic) image when combined with an off-the-shelf image-to-3D model. We further introduce a new challenging benchmark for 3D articulation estimation curated from high-quality public 3D assets, and redesign the evaluation protocol to be more consistent with human preferences. Empirically, Particulate significantly outperforms state-of-the-art approaches.
title Particulate: Feed-Forward 3D Object Articulation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2512.11798