Metraipolis › archive › dc_2ea258b2bf9c

GeoWM: Efficient Direct World Modeling in Explicit Geometry — arXiv:2610.07381

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.07381
License (as archived): CC0-1.0
Archived: 2026-10-07T13:07:07.404Z
SHA-256 of the archived text: 762016a43964bfd2ddda17fb6231b9d47138f9f881472c856cb935eacede3176
Stable URL of this page: https://metraipolis.com/documento/dc_2ea258b2bf9c

How to cite

GeoWM: Efficient Direct World Modeling in Explicit Geometry — arXiv:2610.07381 — arXiv (en), https://arxiv.org/abs/2610.07381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ea258b2bf9c (Metraipolis archive dc_2ea258b2bf9c, sha256 762016a43964bfd2ddda17fb6231b9d47138f9f881472c856cb935eacede3176)

BibTeX

@misc{dc2ea258b2bf9c,
  title = {GeoWM: Efficient Direct World Modeling in Explicit Geometry — arXiv:2610.07381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ea258b2bf9c; sha256 762016a43964bfd2ddda17fb6231b9d47138f9f881472c856cb935eacede3176},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modeling 3D scene geometry and its evolution over time is essential for autonomous driving and robotics. A common paradigm is to use world models to predict future images or latent representations of the environment and subsequently recover geometry from these predictions. However, this paradigm does not explicitly model geometric structure and typically relies on recursive rollouts to reach longer prediction horizons, leading to error accumulation and increasing computational cost. To address these limitations, we present GeoWM, a geometry world model that directly forecasts future scene geometry at specified future horizons without recursive rollout. The key idea is to leverage a geometry foundation model to transform observed RGB frames into a geometric history, which conditions a flow-matching transformer to predict the scene geometry at a specified future horizon. We further show that a lightweight camera-motion predictor can accurately estimate the future viewpoint, and that projecting the observed geometry into the predicted viewpoint provides an effective geometric prior for future geometry forecasting. Extensive experiments on four datasets spanning urban driving, aerial flight, and dynamic manipulation demonstrate that GeoWM outperforms the evaluated world models in forecasting depth, camera pose, and 3D scene geometry, while substantially reducing inference time at longer horizons.

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/2610.07381 — 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 2026-10-07T12:37:32.882Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).