{"ID":2867530,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17427","arxiv_id":"2509.17427","title":"Single-Image Depth from Defocus with Coded Aperture and Diffusion Posterior Sampling","abstract":"We propose a single-snapshot depth-from-defocus (DFD) reconstruction method for coded-aperture imaging that replaces hand-crafted priors with a learned diffusion prior used purely as regularization. Our optimization framework enforces measurement consistency via a differentiable forward model while guiding solutions with the diffusion prior in the denoised image domain, yielding higher accuracy and stability than classical optimization. Unlike U-Net-style regressors, our approach requires no paired defocus-RGBD training data and does not tie training to a specific camera configuration. Experiments on comprehensive simulations and a prototype camera demonstrate consistently strong RGBD reconstructions across noise levels, outperforming both U-Net baselines and a classical coded-aperture DFD method.","short_abstract":"We propose a single-snapshot depth-from-defocus (DFD) reconstruction method for coded-aperture imaging that replaces hand-crafted priors with a learned diffusion prior used purely as regularization. Our optimization framework enforces measurement consistency via a differentiable forward model while guiding solutions wi...","url_abs":"https://arxiv.org/abs/2509.17427","url_pdf":"https://arxiv.org/pdf/2509.17427v1","authors":"[\"Hodaka Kawachi\",\"Jose Reinaldo Cunha Santos A. V. Silva Neto\",\"Yasushi Yagi\",\"Hajime Nagahara\",\"Tomoya Nakamura\"]","published":"2025-09-22T07:20:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}