Metraipolis › archive › dc_c98fc0a49df9
One Model, Two Worlds: Bidirectional Sonar-Optical Translation — arXiv:2609.06253
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06253
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:06:54.201Z
- SHA-256 of the archived text
c9b383625e9ef5118acd65345a497af5082a1a60a4609cdcb612ccb866341ffe- Stable URL of this page
https://metraipolis.com/documento/dc_c98fc0a49df9
How to cite
One Model, Two Worlds: Bidirectional Sonar-Optical Translation — arXiv:2609.06253 — arXiv (en), https://arxiv.org/abs/2609.06253 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c98fc0a49df9 (Metraipolis archive dc_c98fc0a49df9, sha256 c9b383625e9ef5118acd65345a497af5082a1a60a4609cdcb612ccb866341ffe)
BibTeX
@misc{dcc98fc0a49df9,
title = {One Model, Two Worlds: Bidirectional Sonar-Optical Translation — arXiv:2609.06253},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06253},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c98fc0a49df9; sha256 c9b383625e9ef5118acd65345a497af5082a1a60a4609cdcb612ccb866341ffe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06253. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Translating between imaging sonar and optical cameras is valuable for underwater perception, but supporting both directions with separate models duplicates storage and computation. A unified bidirectional model is therefore attractive, yet existing approaches largely treat the two directions symmetrically despite their fundamentally different image-formation physics. We argue that sharing a generative model does not require sharing the physics. We introduce the Direction-Asymmetric Realism Bridge (DARB), which retains a shared diffusion-bridge trunk while routing direction-specific physical priors through asymmetric pathways: range-aware modulation for sonar-to-optical translation and polar ray-dependent processing for optical-to-sonar translation. We further show that symmetry in training is also costly: applying a common realism schedule reduces sonar-to-optical PSNR by 2.60 dB. Our Adaptive Realism Supervision (ARS) instead determines when, where, and how strongly perceptual supervision is applied from reconstruction quality and gradient balance. Together, DARB and ARS enable one bidirectional model to match the sonar-to-optical specialist within 0.11 dB PSNR, outperform the optical-to-sonar specialist by 0.70 FID, and surpass two independently trained BBDMs on seven of eight metrics. 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/2609.06253 — 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 2026-10-16T14:49:57.063Z 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).