Metraipolis › archive › dc_5dec90b2ca4d
EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video — arXiv:2610.40832
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40832
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:20:22.176Z
- SHA-256 of the archived text
a8b24f80fb4f674c06f39e16cd0baecfbc8a5d2ce6c0dfe1eafd7d82a88eddd8- Stable URL of this page
https://metraipolis.com/documento/dc_5dec90b2ca4d
How to cite
EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video — arXiv:2610.40832 — arXiv (en), https://arxiv.org/abs/2610.40832 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5dec90b2ca4d (Metraipolis archive dc_5dec90b2ca4d, sha256 a8b24f80fb4f674c06f39e16cd0baecfbc8a5d2ce6c0dfe1eafd7d82a88eddd8)
BibTeX
@misc{dc5dec90b2ca4d,
title = {EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video — arXiv:2610.40832},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40832},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5dec90b2ca4d; sha256 a8b24f80fb4f674c06f39e16cd0baecfbc8a5d2ce6c0dfe1eafd7d82a88eddd8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40832. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Egocentric videos offer an abundant source of hand-scene interactions for embodied learning, which requires recovering hands, camera, and scene consistently in a shared 3D world. Existing methods focus on either camera-frame hands or world-space hand trajectories, without jointly recovering the scene pointmaps or interaction information. Building a complete reconstruction from such specialized predictions therefore typically requires per-sequence optimization. We propose EgoHSI3R, a unified feed-forward framework for online 4D hand-scene interaction reconstruction from egocentric monocular video. To jointly recover these components, it maintains a recurrent scene representation that accumulates geometric evidence over time and provides a shared world space and scale. We introduce hand-centric prompts that fuse pretrained hand priors and local scene context, while MANO vertex queries attend to scene features to predict dense per-vertex contact. These designs enable a single network to jointly estimate camera motion, dense scene geometry, world-space bilateral MANO hands, and per-vertex hand contact. Despite operating causally, EgoHSI3R achieves the lowest world-space hand joint error on ARCTIC among the evaluated methods, while offering faster inference than existing world-space hand reconstruction pipelines and competitive camera and scene reconstruction 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/2610.40832 — 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 2026-11-03T08:06:38.807Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).