Metraipolis › archive › dc_0fca052f3de3
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling — arXiv:2610.22343
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22343
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:50:58.960Z
- SHA-256 of the archived text
9dc370812efb13eee91fa54e391319cc070a72c912645edeace535f1390b9add- Stable URL of this page
https://metraipolis.com/documento/dc_0fca052f3de3
How to cite
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling — arXiv:2610.22343 — arXiv (en), https://arxiv.org/abs/2610.22343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fca052f3de3 (Metraipolis archive dc_0fca052f3de3, sha256 9dc370812efb13eee91fa54e391319cc070a72c912645edeace535f1390b9add)
BibTeX
@misc{dc0fca052f3de3,
title = {GeoState: Learning View-Decoupled Geometry States for 3D World Modeling — arXiv:2610.22343},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22343},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fca052f3de3; sha256 9dc370812efb13eee91fa54e391319cc070a72c912645edeace535f1390b9add},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynamics with camera-induced variation, making the resulting state evolution harder to predict. We propose GeoState, a view-decoupled geometry representation for predictive 3D world modeling that separates scene-state evolution from camera-dependent observation. Specifically, a scene tokenizer aggregates multi-view GFM features into a view-decoupled scene state, which a geometry decoder queries using camera rays. An autoregressive world model then predicts future scene states, while camera motion is modeled separately. The predicted states can therefore be decoded under either predicted or externally specified cameras, while retaining a single context-derived scale throughout the rollout without per-frame scale alignment. Experiments show that GeoState outperforms prior 3D world models on Waymo, supports geometrically consistent cross-view querying, and generalizes zero-shot to KITTI and nuScenes. Project page: this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.22343 — 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 2026-10-16T08:44:18.065Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).