Metraipolis › archive › dc_72be7fa58211
Ordered Diffusion for 3D Human Registration — arXiv:2608.05804
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05804
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:16.580Z
- SHA-256 of the archived text
1e7ba6ad116b6a8b38e23b44ff508b44123f7402a7e1e72658668f80a5158d32- Stable URL of this page
https://metraipolis.com/documento/dc_72be7fa58211
How to cite
Ordered Diffusion for 3D Human Registration — arXiv:2608.05804 — arXiv (en), https://arxiv.org/abs/2608.05804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_72be7fa58211 (Metraipolis archive dc_72be7fa58211, sha256 1e7ba6ad116b6a8b38e23b44ff508b44123f7402a7e1e72658668f80a5158d32)
BibTeX
@misc{dc72be7fa58211,
title = {Ordered Diffusion for 3D Human Registration — arXiv:2608.05804},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05804},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_72be7fa58211; sha256 1e7ba6ad116b6a8b38e23b44ff508b44123f7402a7e1e72658668f80a5158d32},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
3D human registration has historically been treated as a regression task, assuming a unique ground-truth alignment exists between the template and an input point cloud. In reality, acquisition noise, occlusions, and unknown soft tissue dynamics introduce inherent ambiguity into human scans. Regression-based methods consequently converge to an average prediction, often failing to represent a plausible geometry. In our work, we embrace such uncertainty by modeling the registration as a distribution of alignments. We propose ODin, which formulates registration as a 3D diffusion process that generates a point cloud aligned with the target geometry while preserving template semantics through consistent point ordering. To achieve this, ODin relies on global, local, and positional conditioning, guiding each point to its correct location. Our experiments demonstrate that such a generative formulation not only outperforms its regression-based baseline, but also establishes a new state of the art, surpassing highly engineered methods while reducing the registration time by two-thirds. Pre-trained models and code are available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05804 — 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 2026-10-31T10:23:31.020Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).