Metraipolis › archive › dc_33669cf5ced5
CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments — arXiv:2610.03031
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.03031
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:07:37.106Z
- SHA-256 of the archived text
c56f96ecd96d1af902eb9318d65e70a95ce4c4b4ba39f2718ed62908f781cea0- Stable URL of this page
https://metraipolis.com/documento/dc_33669cf5ced5
How to cite
CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments — arXiv:2610.03031 — arXiv (en), https://arxiv.org/abs/2610.03031 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33669cf5ced5 (Metraipolis archive dc_33669cf5ced5, sha256 c56f96ecd96d1af902eb9318d65e70a95ce4c4b4ba39f2718ed62908f781cea0)
BibTeX
@misc{dc33669cf5ced5,
title = {CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments — arXiv:2610.03031},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.03031},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33669cf5ced5; sha256 c56f96ecd96d1af902eb9318d65e70a95ce4c4b4ba39f2718ed62908f781cea0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.03031. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Monocular semantic scene completion (SSC) for quadruped robots remains underexplored in real crowded indoor environments, where human-scene occlusion disrupts static geometry and human occupancy predictions are often incomplete or spatially misplaced. We present CrowdOcc, an RGB-D dataset and monocular SSC framework for this setting. CrowdOcc contains 25.1K frames from 11 indoor scenes, with semantic occupancy annotations constructed through static dynamic decoupling. Our framework combines: (i) Normal Guided Scene Geometry Fusion (NGSGF) to complement depth-aware lifting with surface-normal cues for occlusion robust geometry; and (ii) Human-Centric Sparse Interaction (HCSI) to selectively model human-human and local human scene relations in 3D. Our method achieves state-of-the-art SSC performance on CrowdOcc's scene-disjoint test set, reaching 15.80 IoU, 11.40 mIoU, and 46.23 Human IoU, demonstrating generalization to unseen indoor scenes. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.03031 — 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 2026-10-06T08:21:44.196Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).