Research map / Image generation / Image restoration
Learning Deep Priors for Image Dehazing
Yang Liu, Jinshan Pan, Jimmy Ren, Zhixun Su
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 learned prior network NJ for the clear image (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.25 -> 24.71 | Improved |
| add learned prior network NJ for the clear image (ablation) | Ours · SOTS | PSNR (dB): 22.03 -> 22.46 | Improved |
| add learned prior network NJ for the clear image (ablation) | Ours · HazeRD | PSNR (dB): 17.45 -> 17.51 | No clear effect |
| add all three learned prior networks NA, Nt, NJ (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.24 -> 24.71 | Improved |
| add all three learned prior networks NA, Nt, NJ (ablation) | Ours · SOTS | PSNR (dB): 21.94 -> 22.46 | Improved |
| add all three learned prior networks NA, Nt, NJ (ablation) | Ours · HazeRD | PSNR (dB): 17.24 -> 17.51 | Improved |
| add learned prior network Nt for transmission (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.49 -> 24.71 | Improved |
| add learned prior network NA for atmospheric light (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.70 -> 24.71 | No clear effect |
| add data-fidelity terms F and G (ablation) | Ours · SOTS | PSNR (dB): 22.32 -> 22.46 | Improved |
| add data-fidelity terms F and G (ablation) | Ours · HazeRD | PSNR (dB): 17.31 -> 17.51 | Improved |
| add data-fidelity term F (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.69 -> 24.71 | No clear effect |
| add data-fidelity term G (ablation) | Ours · Synthetic (300 images) | PSNR (dB): 24.67 -> 24.71 | No clear effect |
Closest papers by meaning
- Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing (ECCV 2018 · similarity 0.91)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.90)
- Learning to dehaze with polarization (NeurIPS 2021 · similarity 0.90)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.89)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.88)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · 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.
