Research map / Label-efficient and robust learning / Self-supervised and contrastive
Boosting Supervised Dehazing Methods via Bi-Level Patch Reweighting
Xingyu Jiang, Hongkun Dou, Chengwei Fu, Bingquan Dai, Tianrun Xu, Yue Deng
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 BILD bi-level patch reweighting | FFANet · SOTS indoor | PSNR (dB): 31.44 -> 32.14 | Improved |
| add BILD bi-level patch reweighting | FFANet · O-HAZE | PSNR (dB): 24.13 -> 24.91 | Improved |
| add BILD bi-level patch reweighting | FFANet · NH-HAZE | PSNR (dB): 18.04 -> 19.13 | Improved |
| add BILD bi-level patch reweighting | AODNet · O-HAZE | PSNR (dB): 18.07 -> 20.81 | Improved |
| add BILD bi-level patch reweighting | MSBDN · SOTS indoor | PSNR (dB): 28.66 -> 29.69 | Improved |
| add BILD bi-level patch reweighting | MSBDN · SOTS outdoor | PSNR (dB): 26.94 -> 27.03 | Improved |
| add BILD bi-level patch reweighting | GridDehazeNet · SOTS indoor | PSNR (dB): 28.22 -> 28.87 | Improved |
| add BILD bi-level patch reweighting | DehazeNet · SOTS indoor | PSNR (dB): 20.56 -> 21.15 | Improved |
| add BILD with external loop objective on validation set rather than training set (ablation) | FFANet · SOTS indoor | PSNR (dB): 31.53 -> 32.14 | Improved |
| add BILD with external loop objective on validation set rather than training set (ablation) | MSBDN · SOTS indoor | PSNR (dB): 28.92 -> 29.69 | Improved |
| add an external reweighting loop objective defined on training set only (ablation) | FFANet · SOTS indoor | PSNR (dB): 31.44 -> 31.53 | Improved |
| add BILD when training on full ITS | FFANet · Full ITS indoor | PSNR (dB): 36.39 -> 38.58 | Improved |
Closest papers by meaning
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.88)
- Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation (AAAI 2026 · similarity 0.87)
- CoA: Towards Real Image Dehazing via Compression-and-Adaptation (CVPR 2025 · similarity 0.86)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.86)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.85)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · 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.
