Research map / Image generation / Image restoration
Perceiving and Modeling Density for Image Dehazing
Tian Ye, Yunchen Zhang, Mingchao Jiang, Liang Chen, Yun Liu, Sixiang Chen, Erkang Chen
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 haze density encoding matrix (vs identity matrix) (ablation) | PMDNet · Haze4K | PSNR: 30.33 -> 33.49 | Improved |
| use unsupervised density encoding matrix instead of GT transmission map (ablation) | PMDNet · Haze4K | PSNR: 31.42 -> 33.49 | Improved |
| use unsupervised density encoding matrix instead of estimated transmission map (ablation) | PMDNet · Haze4K | PSNR: 31.17 -> 33.49 | Improved |
| use density encoding matrix instead of normalized difference map (ablation) | PMDNet · Haze4K | PSNR: 32.21 -> 33.49 | Improved |
| replace residual blocks with SHA attention (ablation) | Baseline dehazing net · Haze4K | PSNR: 24.40 -> 26.39 | Improved |
| use SHA instead of SWRCA attention (ablation) | Baseline dehazing net · Haze4K | PSNR: 25.87 -> 26.39 | Improved |
| use SHA instead of FA attention (ablation) | Baseline dehazing net · Haze4K | PSNR: 25.30 -> 26.39 | Improved |
| use FA attention instead of CBA (ablation) | Baseline dehazing net · Haze4K | PSNR: 25.36 -> 25.30 | Hurt |
| extend SHA to multi-branch MHAB (ablation) | Baseline dehazing net · Haze4K | PSNR: 26.39 -> 27.02 | Improved |
| add contextual transformer branch (MHA-C vs MHAB) (ablation) | Baseline dehazing net · Haze4K | PSNR: 27.02 -> 27.58 | Improved |
| PMDNet vs second-best method | PMDNet · Haze4K | PSNR: 28.53 -> 33.49 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FFA-Net — FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (AAAI 2020) · better on 6 of 6 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
- Advancing Real-World Image Dehazing: Perspective, Modules, and Training (TPAMI 2024 · similarity 0.91)
- Towards Domain Invariant Single Image Dehazing (AAAI 2021 · similarity 0.89)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.89)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.89)
- Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images (CVPR 2025 · similarity 0.87)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (NeurIPS 2024 · similarity 0.87)
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.
