Metraipolis › archive › dc_d9ac05157bee
LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting — arXiv:2611.11912
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11912
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:43:45.632Z
- SHA-256 of the archived text
c48ef537fa4f0bd863e97c43e85f93e4d4de69b9867a0968eba6dadd4cb01107- Stable URL of this page
https://metraipolis.com/documento/dc_d9ac05157bee
How to cite
LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting — arXiv:2611.11912 — arXiv (en), https://arxiv.org/abs/2611.11912 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d9ac05157bee (Metraipolis archive dc_d9ac05157bee, sha256 c48ef537fa4f0bd863e97c43e85f93e4d4de69b9867a0968eba6dadd4cb01107)
BibTeX
@misc{dcd9ac05157bee,
title = {LO-World: Unified BEV Latent Modeling for Joint 4D Occupancy and LiDAR Forecasting — arXiv:2611.11912},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11912},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d9ac05157bee; sha256 c48ef537fa4f0bd863e97c43e85f93e4d4de69b9867a0968eba6dadd4cb01107},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11912. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LiDAR point clouds and 3D semantic occupancy represent two distinct modalities capturing fine-grained metric geometry and dense volumetric semantics, respectively, holding natural potential for mutual complementarity. However, existing world models typically forecast these modalities independently or cascade them heuristically, missing the opportunity for reciprocal cross-modal regularization. To address this, we propose \textbf{LO-World}, a unified 4D world model that forecasts both modalities within a shared BEV latent space. This single-stream formulation enables dense semantics and metric geometry to mutually reinforce each other, while eliminating multi-pipeline redundancy. Specifically, LO-World couples an efficient hybrid range-voxel autoencoder with a flow-matching generator that caches historical context to reduce iterative sampling latency. Extensive experiments demonstrate that LO-World outperforms prior state-of-the-art baselines, improving occupancy forecasting IoU by 10.9% and reducing LiDAR Chamfer Distance by 30.1%. Meanwhile, it sustains a real-time throughput exceeding $25$~FPS on a single RTX 4090. Our code is available at 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).
Pagina del lavoro: https://arxiv.org/abs/2611.11912 — 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 2026-11-10T18:37:37.666Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).