Metraipolis › archive › dc_1329a1db7bec

Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction — arXiv:2608.10682

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10682
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:22.106Z
SHA-256 of the archived text
9ec4ecb1c7bab871fcc90bcebe72271898918edde80d8ca37f303ba07222b454
Stable URL of this page
https://metraipolis.com/documento/dc_1329a1db7bec

How to cite

Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction — arXiv:2608.10682 — arXiv (en), https://arxiv.org/abs/2608.10682 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1329a1db7bec (Metraipolis archive dc_1329a1db7bec, sha256 9ec4ecb1c7bab871fcc90bcebe72271898918edde80d8ca37f303ba07222b454)
BibTeX
@misc{dc1329a1db7bec,
  title = {Visual Geometry Foundation-Aware Gaussians for Single-Frame Surround-View Driving Reconstruction — arXiv:2608.10682},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10682},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1329a1db7bec; sha256 9ec4ecb1c7bab871fcc90bcebe72271898918edde80d8ca37f303ba07222b454},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10682. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Single-frame surround-view reconstruction faces severe geometric instability and rendering artifacts due to minimal inter-camera overlap. While existing methods rely on complex decoders or auxiliary cues, they remain bottlenecked by the weak geometric capacity of upstream features. We argue that leveraging pretrained visual geometry priors strengthens upstream representations and alleviates the geometric ambiguity in sparse surround views. To this end, we propose VGGD, a visual geometry foundation-aware 3D Gaussian Splatting framework for feed-forward surround-view driving reconstruction, which shifts geometric modeling to the frontend and adapts foundation priors to the driving camera setting. First, VGGD leverages VGGT to provide transferable multi-view geometric prior tokens. Next, we introduce a Dual-Path Neck to decouple geometry-consistent and appearance-aware representations, improving appearance completion in weakly observed regions. We further apply Scale Warmup to stabilize early geometry learning and suppress scale drift under ego-pose changes. Finally, we use a hybrid pixel--volume Gaussian decoder to produce a renderable 3D Gaussian scene for novel-view synthesis. Experiments on the nuScenes single-frame benchmark show that VGGD achieves the best overall rendering quality among the compared methods and improves relative geometric consistency.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10682 — 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 2026-10-19T06:25:27.270Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).