Research map / 3D vision / Depth and stereo
What Is the Space of Attenuation Coefficients in Underwater Computer Vision?
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Constrain RGB attenuation coefficients to the oceanic and coastal loci derived from Jerlov water types | Underwater image reconstruction · Jerlov water types | feasible coefficient space: from the entire R3 to a limited manifold | Helped |
| Use the predicted locus allowing range, radiance, and water type to vary | RGB effective attenuation coefficient model · Mediterranean Sea and Red Sea | agreement with observed coefficients | Helped |
| Account for object range when estimating effective attenuation coefficients | Underwater color reconstruction · Simulated Macbeth ColorChecker | relative reconstruction error: eJ/J = zeβ | Helped |
| Account for object reflectance when estimating effective attenuation coefficients | Underwater color reconstruction · Macbeth ColorChecker patches | reconstruction color error | Helped |
| Use a single wideband attenuation coefficient independent of scene properties | Common underwater image formation model · Underwater image reconstruction | reconstruction error: 14% | Hurt |
Closest papers by meaning
- Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion (CVPR 2024 · similarity 0.84)
- Dive into Aerial Remote Sensing Underwater Depth Estimation with Hyperspectral Imagery (AAAI 2025 · similarity 0.84)
- Plenodium: Underwater 3D Scene Reconstruction with Plenoptic Medium Representation (NeurIPS 2025 · similarity 0.83)
- Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration (CVPR 2024 · similarity 0.82)
- Adaptive Dual-domain Learning for Underwater Image Enhancement (AAAI 2025 · similarity 0.82)
- Neural Underwater Scene Representation (CVPR 2024 · similarity 0.81)
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.