Research map / Image generation / Image restoration
Osmosis: RGBD Diffusion Prior for Underwater Image Restoration
Opher Bar Nathan, Deborah Levy, Tali Treibitz, Dan Rosenbaum
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add auxiliary value-range and gray-world losses to the reconstruction loss (ablation) | Osmosis · NYU-v2 simulation | PSNR: 21.09 -> 22.74 | Improved |
| weight the reconstruction loss by estimated depth (ablation) | Osmosis · NYU-v2 simulation | PSNR: 22.17 -> 22.74 | Improved |
| use a smaller guidance scale for the depth channel than for RGB (ablation) | Osmosis · NYU-v2 simulation | PSNR: 22.00 -> 22.74 | Improved |
| estimate depth jointly with the image using the RGBD prior instead of a fixed external Depth Anything depth (ablation) | Osmosis · 50 real-world images | MUSIQ: 51.23 -> 56.62 | Improved |
| allow separate attenuation and backscatter coefficients instead of tying them (ablation) | Osmosis · real-world images | restoration range | Improved |
| remove the value-range loss (ablation) | Osmosis · real-world images | color quality | Hurt |
| remove the gray-world average loss (ablation) | Osmosis · real-world images | color quality | Hurt |
| train the prior on in-air RGBD data only, with no underwater images | Osmosis · NYU-v2 simulation | PSNR: 18.04 (UW-Net) -> 22.74 | Improved |
| feed non-linear images instead of linear images | Osmosis · non-linear inputs | restoration range | Hurt |
Later papers that compared with this method
1 later accepted paper reports Osmosis as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Single-Step Latent Diffusion for Underwater Image Restoration (TPAMI 2025 · better on 11 of 11 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Single-Step Latent Diffusion for Underwater Image Restoration (TPAMI 2025 · similarity 0.91)
- Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion (CVPR 2024 · similarity 0.87)
- WaterDiffusion: Learning a Prior-involved Unrolling Diffusion for Joint Underwater Saliency Detection and Visual Restoration (AAAI 2025 · similarity 0.87)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.85)
- Learning Diffusion Texture Priors for Image Restoration (CVPR 2024 · similarity 0.85)
- Blind Image Restoration via Fast Diffusion Inversion (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
