Metraipolis › archive › dc_ee8734e6c614
Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery — arXiv:2610.10512
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10512
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:48:22.187Z
- SHA-256 of the archived text
86fa52a13983032b24c4e039c4df98b22ed35454c970219ab6e19dffbe584411- Stable URL of this page
https://metraipolis.com/documento/dc_ee8734e6c614
How to cite
Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery — arXiv:2610.10512 — arXiv (en), https://arxiv.org/abs/2610.10512 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee8734e6c614 (Metraipolis archive dc_ee8734e6c614, sha256 86fa52a13983032b24c4e039c4df98b22ed35454c970219ab6e19dffbe584411)
BibTeX
@misc{dcee8734e6c614,
title = {Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery — arXiv:2610.10512},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10512},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee8734e6c614; sha256 86fa52a13983032b24c4e039c4df98b22ed35454c970219ab6e19dffbe584411},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10512. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recovering faithful 3D hand motion from video remains challenging due to frequent occlusions and incomplete visual observations, which make frame-wise pose estimates unreliable and temporally inconsistent. To address this problem, we propose JoHan, a unified generative framework that recovers hand motion directly from video sequences without relying on intermediate per-frame pose predictions. Trained from scratch, our model jointly generates aligned 2D and 3D local hand pose sequences by learning their temporal dynamics and cross-representation correspondence. The generated 2D trajectories exploit direct spatial and temporal cues from the 2D images to guide the following generative 3D motion reconstruction, while the learned motion prior promotes temporal consistency. Their learned 2D-3D correspondence further enables recovery of the hand's global position and orientation relative to the camera. Extensive experiments on challenging benchmarks demonstrate significantly improved accuracy and speed in local hand-pose and camera-space reconstruction. Notably, our method captures much better hand-motion dynamics, producing significantly smoother motion than previous methods while maintaining high per-frame pose accuracy. 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/2610.10512 — 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 2026-10-08T12:18:15.510Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).