{"ID":5937692,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T13:43:20.341700643Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04303","arxiv_id":"2607.04303","title":"AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation","abstract":"Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distillation strategy that jointly address data scarcity and feature degradation in underwater stereo matching. First, a depth-conditioned diffusion pipeline renders underwater stereo pairs while preserving binocular geometry, with a lightweight left-right consistency module ensuring geometric alignment. Training on this synthetic corpus effectively narrows the terrestrial-underwater gap and improves zero-shot robustness. Second, a frozen binocular teacher trained on clean terrestrial pairs guides a student exposed to rendered underwater pairs with perturbations. A stage-weighted sequence loss is performed to align the student's disparities with the teacher's geometry, while a clean-branch supervision with shared pseudo targets prevents scale drift. To further enhance feature stability under turbidity and low texture, we introduce learnable perception frames, a perception-enhanced feature formulation that constructs robust matching descriptors by fusing temporal cues from two auxiliary views encoded by a video backbone with semantic features extracted by a strong image encoder. Extensive experiments demonstrate that $\\textbf{AquaStereo}$ substantially improves robustness and zero-shot generalization in challenging underwater scenarios. The code is available at https://github.com/qz-wei/AquaStereo.","short_abstract":"Learning-based stereo matching models struggle in underwater environments due to scarce in-domain data and the difficulty of extracting discriminative correspondences from degraded imagery. In this work, we present $\\textbf{AquaStereo}$, a perception-enhanced framework with a data simulation pipeline and a self-distill...","url_abs":"https://arxiv.org/abs/2607.04303","url_pdf":"https://arxiv.org/pdf/2607.04303v1","authors":"[\"Qizhe Wei\",\"Yingping Liang\",\"Shaodi You\",\"Ying Fu\"]","published":"2026-07-05T13:43:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":613981,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5937692,"paper_url":"https://arxiv.org/abs/2607.04303","paper_title":"AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillation","repo_url":"https://github.com/qz-wei/AquaStereo","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}