Research map / Image generation / Image restoration
Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training
Read the paperCheck 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 |
|---|---|---|---|
| physics-based disentanglement with unpaired adversarial training vs CycleGAN | unpaired dehazing · D-HAZY NYU-Depth | PSNR: 13.3879 -> 15.5456 | Helped |
| physics-based disentanglement vs CycleGAN | unpaired dehazing · D-HAZY Middlebury cross-domain | PSNR: 11.3037 -> 14.9539 | Helped |
| multi-scale discriminator instead of local discriminator (ablation) | Disentangled Dehazing Network · D-HAZY NYU-Depth | PSNR: 13.7518 -> 15.6440 | Helped |
| multi-scale discriminator instead of global discriminator (ablation) | Disentangled Dehazing Network · D-HAZY NYU-Depth | SSIM: 0.6779 -> 0.7432 | Helped |
| blend generator output with transmission-based recovery (ablation) | Disentangled Dehazing Network · D-HAZY NYU-Depth | SSIM: 0.7432 -> 0.7726 | Helped |
| blend generator output with transmission-based recovery (ablation) | Disentangled Dehazing Network · D-HAZY NYU-Depth | PSNR: 15.644 -> 15.5456 | No clear effect |
| train without corresponding hazy/haze-free scenes (ablation) | Disentangled Dehazing Network · D-HAZY NYU-Depth split 2 | PSNR: 15.2269 -> 14.7460 | Hurt |
Closest papers by meaning
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.89)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.87)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (NeurIPS 2024 · similarity 0.87)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.86)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.86)
- PEIE: Physics Embedded Illumination Estimation for Adaptive Dehazing (AAAI 2025 · similarity 0.86)
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.