Metraipolis › archive › dc_25d249d36d92
ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation — arXiv:2611.07658
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.07658
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-06T14:53:28.279Z
- SHA-256 of the archived text
2945472f8e8b257adfd1f587d380880454d69be137d156207e4ea48989f631eb- Stable URL of this page
https://metraipolis.com/documento/dc_25d249d36d92
How to cite
ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation — arXiv:2611.07658 — arXiv (en), https://arxiv.org/abs/2611.07658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25d249d36d92 (Metraipolis archive dc_25d249d36d92, sha256 2945472f8e8b257adfd1f587d380880454d69be137d156207e4ea48989f631eb)
BibTeX
@misc{dc25d249d36d92,
title = {ArtCrafter: Feed-Forward Generation of Articulated 3D Object with Analytic Joint Derivation — arXiv:2611.07658},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.07658},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25d249d36d92; sha256 2945472f8e8b257adfd1f587d380880454d69be137d156207e4ea48989f631eb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Articulated 3D assets are essential for robotic simulation and training, yet their generation from casual images poses a key challenge: recovering part geometry and kinematics that remain mutually consistent. We present ArtCrafter, a novel feed-forward generative model for controllable generation of articulated 3D objects from a pair of images, one depicting the object in the rest state and the other in the open state. At the core of ArtCrafter is a DiT-based generative model that jointly produces part-level meshes for both articulation states in a single forward pass. Inspired by Slot Attention, its denoising process operates on a $1+2N$ slot layout comprising one shared base slot and $N$ paired rest/open slots, encouraging each pair to bind to the same kinematic part. To ensure geometrically consistent and disjoint part generation, we introduce Triplet Attention to enforce cross-state geometric consistency between paired rest/open slots anchored through the shared base slot, and a repulsion loss $\mathcal{L}_{\mathrm{rep}}$ on decoded part point clouds to prevent inter-part penetration throughout denoising. Given the resulting paired meshes, URDF joint parameters---type, axis, origin, and range---are derived analytically from the rigid transformation between each rest/open pair, providing an interpretable alternative to learned joint-parameter regression. Extensive experiments on both in-distribution and out-of-distribution datasets demonstrate that ArtCrafter outperforms existing method under the same dual-state setting in geometry quality and articulation precision, while remaining competitive with methods operating under different input settings and paradigms.
Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.07658 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-06T14:25:42.614Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).