Research map / 3D vision / Depth and stereo
Learning to dehaze with polarization
Chu Zhou, Minggui Teng, Yufei Han, Chao Xu, Boxin Shi
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 |
|---|---|---|---|
| model polarization of transmitted light (P_T) instead of ignoring it (ablation) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 27.63 -> 28.32 | Improved |
| model spatially-variant scattering instead of uniform (ablation) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 27.86 -> 28.32 | Improved |
| estimate physical parameters (P_T, P_A, A_inf) instead of directly estimating T and R (ablation) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 27.27 -> 28.32 | Improved |
| add refinement subnetwork g2 for transmitted light (ablation) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 21.55 -> 28.32 | Improved |
| add refinement subnetwork g4 for scene radiance (ablation) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 21.28 -> 28.32 | Improved |
| add both refinement subnetworks (ablation) | polarization dehazing network · synthetic polarized haze | MS-SSIM: 0.662 -> 0.951 | Improved |
| use polarized-image network instead of optimization-based SPCVE | polarization dehazing network · synthetic polarized haze | PSNR (dB): 15.94 -> 28.32 | Improved |
| use polarized inputs instead of single-image dehazing (MSBDN) | polarization dehazing network · synthetic polarized haze | PSNR (dB): 26.94 -> 28.32 | Improved |
Closest papers by meaning
- Learning Deep Priors for Image Dehazing (ICCV 2019 · similarity 0.90)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.88)
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing (NeurIPS 2026 · similarity 0.88)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.86)
- Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images (CVPR 2025 · similarity 0.86)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (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.
