Metraipolis › archive › dc_41f4bef0f22c

VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors — arXiv:2609.19628

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19628
License (as archived)
CC0-1.0
Archived
2026-10-10T05:05:27.359Z
SHA-256 of the archived text
33dd07513f272bc0de139123a21929e41fde944b4d7aa5885ccffd8d3bb8e81f
Stable URL of this page
https://metraipolis.com/documento/dc_41f4bef0f22c

How to cite

VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors — arXiv:2609.19628 — arXiv (en), https://arxiv.org/abs/2609.19628 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41f4bef0f22c (Metraipolis archive dc_41f4bef0f22c, sha256 33dd07513f272bc0de139123a21929e41fde944b4d7aa5885ccffd8d3bb8e81f)
BibTeX
@misc{dc41f4bef0f22c,
  title = {VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors — arXiv:2609.19628},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19628},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41f4bef0f22c; sha256 33dd07513f272bc0de139123a21929e41fde944b4d7aa5885ccffd8d3bb8e81f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19628. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present VGGT-GS SLAM, a monocular 3D Gaussian Splatting SLAM system designed for uncalibrated videos. Starting from feed-forward VGGT pose and depth priors, our system performs submap differentiable bundle adjustment that jointly refines camera poses and a 3D Gaussian map, while optimizing submap-shared intrinsics and radial--tangential distortion through analytic calibration Jacobians. To improve global consistency, we introduce Gaussian-native alignment (GNA) for camera-anchored scale refinement between sequential submaps and verification of loop-closure candidates. Extensive experiments on standard indoor benchmarks show consistent improvements in localization accuracy and strong rendering quality under uncalibrated settings, establishing a strong baseline for uncalibrated Gaussian SLAM.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.19628 — 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 2026-10-10T04:26:09.515Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).