Metraipolis › archive › dc_4d44c3a416bc
Adapting Vision Foundation Models to Acoustics for Pose-Free 3D Sonar Reconstruction — arXiv:2609.06261
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06261
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:06:59.879Z
- SHA-256 of the archived text
622e44b888a07483d5ac095d062361381fde8fc8673fa44ccfdea99805890f88- Stable URL of this page
https://metraipolis.com/documento/dc_4d44c3a416bc
How to cite
Adapting Vision Foundation Models to Acoustics for Pose-Free 3D Sonar Reconstruction — arXiv:2609.06261 — arXiv (en), https://arxiv.org/abs/2609.06261 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d44c3a416bc (Metraipolis archive dc_4d44c3a416bc, sha256 622e44b888a07483d5ac095d062361381fde8fc8673fa44ccfdea99805890f88)
BibTeX
@misc{dc4d44c3a416bc,
title = {Adapting Vision Foundation Models to Acoustics for Pose-Free 3D Sonar Reconstruction — arXiv:2609.06261},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06261},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d44c3a416bc; sha256 622e44b888a07483d5ac095d062361381fde8fc8673fa44ccfdea99805890f88},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06261. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision foundation models trained on Internet-scale RGB datasets enable remarkable capabilities across a range of tasks, from text-to-video generation to few-shot 3D scene reconstruction. An acoustic foundation model trained on large-scale sonar datasets could enable similar capabilities in the underwater domain, where turbidity and low-visibility conditions make conventional RGB foundation models inapplicable. Unfortunately, a lack of freely available large-scale sonar datasets makes training such a model from scratch impractical. In this work, we demonstrate that vision foundation models can be efficiently adapted to the sonar setting by (1) exploiting the geometric relationship between the two sensing modalities and (2) employing accurate physics-based noise models for synthetic data generation. The resulting sonar adaptation models enable new capabilities: For the first time, we experimentally demonstrate sonar-based pose-free 3D reconstruction. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.06261 — 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 2026-10-16T14:49:57.065Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).