Metraipolis › archive › dc_dd2ba41d6fc3
Geometry-Grounded Unified 3D Perception for Autonomous Driving — arXiv:2608.13147
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13147
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:55:48.248Z
- SHA-256 of the archived text
f264a0f8e35de8417f97129f29045a0655865f0c7e2ec41c9c903a330965d238- Stable URL of this page
https://metraipolis.com/documento/dc_dd2ba41d6fc3
How to cite
Geometry-Grounded Unified 3D Perception for Autonomous Driving — arXiv:2608.13147 — arXiv (en), https://arxiv.org/abs/2608.13147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd2ba41d6fc3 (Metraipolis archive dc_dd2ba41d6fc3, sha256 f264a0f8e35de8417f97129f29045a0655865f0c7e2ec41c9c903a330965d238)
BibTeX
@misc{dcdd2ba41d6fc3,
title = {Geometry-Grounded Unified 3D Perception for Autonomous Driving — arXiv:2608.13147},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13147},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd2ba41d6fc3; sha256 f264a0f8e35de8417f97129f29045a0655865f0c7e2ec41c9c903a330965d238},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera streams. However, existing image-based frameworks often rely on backbones pretrained for semantic recognition, and introduce 3D geometry through downstream task-specific modules. As a result, their shared representations may fail to preserve explicit metric geometry and consistent 3D scene structure. In this paper, we present a Geometry-grounded Unified 3D Perception (GeoUP) framework that adapts the reconstruction-oriented latent of VGGT to calibrated, streaming multi-camera driving scenes. GeoUP factorizes cross-image interaction into self, temporal, and view attention to capture structurally distinct temporal and cross-view correspondences. It further injects calibration-aware raymap encodings to provide metric scale and camera geometry. The resulting geometry-grounded latent is decoded for metric depth estimation, 3D object detection, and semantic occupancy prediction, corresponding to surface-, instance-, and volume-level readouts of the same 3D scene. Through joint multi-task and multi-dataset training, GeoUP effectively leverages heterogeneous annotations and generalizes across diverse sensor configurations and perception ranges. Extensive experiments on nuScenes, Argoverse 2, Waymo, KITTI, and DDAD demonstrate that GeoUP achieves SOTA performance across detection, occupancy, and depth estimation. These results validate the effectiveness of geometry-grounded representations for unified 3D driving perception. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.13147 — 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 2026-10-19T04:46:30.158Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).