Metraipolis › archive › dc_173da60ae960
Scale Anchoring via Implicit Semantics and Sequence-Consistent Loop Closure for VGGT-Based SLAM — arXiv:2611.06308
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06308
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:30:41.344Z
- SHA-256 of the archived text
5dd1326b67ddbdc0506080c296bbf5efa0af6aacec2ca3168fabfa716a34219d- Stable URL of this page
https://metraipolis.com/documento/dc_173da60ae960
How to cite
Scale Anchoring via Implicit Semantics and Sequence-Consistent Loop Closure for VGGT-Based SLAM — arXiv:2611.06308 — arXiv (en), https://arxiv.org/abs/2611.06308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_173da60ae960 (Metraipolis archive dc_173da60ae960, sha256 5dd1326b67ddbdc0506080c296bbf5efa0af6aacec2ca3168fabfa716a34219d)
BibTeX
@misc{dc173da60ae960,
title = {Scale Anchoring via Implicit Semantics and Sequence-Consistent Loop Closure for VGGT-Based SLAM — arXiv:2611.06308},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06308},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_173da60ae960; sha256 5dd1326b67ddbdc0506080c296bbf5efa0af6aacec2ca3168fabfa716a34219d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward geometric foundation models enable dense monocular reconstruction without requiring camera calibration, but independently reconstructed submaps can accumulate scale drift, and even a valid revisit can yield an inconsistent cross-submap measurement. We extend VGGT-SLAM 2.0 with fixed-root scale anchoring and short-sequence-assisted direct loop connections. SALAD selects an image pair between the initial submap and each eligible new submap; joint VGGT inference then uses learned implicit semantic-geometric cues to supply a scale-only anchor while preserving the original overlap chain. For loop closure, neighboring image pairs support a consistency check and translation-scale alignment. Each accepted candidate contributes one robust Sim(3) factor between existing center-frame nodes, without an auxiliary loop submap. A 17-sequence comparison lowers mean Sim(3) ATE on nine TUM sequences from 0.1018 to 0.0451 m relative to the VGGT-SLAM 2.0 baseline. Anchoring improves all seven no-loop module ablations. On three Clio scenes, a fixed-loop comparison favors the direct connection pipeline over the tested auxiliary-submap pipeline. A separate candidate audit exposes additional rejections of visually overlapping pairs by the short-sequence check. These comparisons distinguish the gains from long-range scale anchoring and loop connection choices from the limitations of candidate verification. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2611.06308 — 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 2026-11-05T18:20:03.988Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).