Research map / Image generation / Image restoration
Domain Adaptation for Image Dehazing
Yuanjie Shao, Lerenhan Li, Wenqi Ren, Changxin Gao, Nong Sang
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 |
|---|---|---|---|
| Apply the full domain adaptation framework | Image dehazing · SOTS | PSNR: 23.82 -> 27.76 | Improved |
| Apply the full domain adaptation framework | Image dehazing · SOTS | SSIM: 0.89 -> 0.93 | Improved |
| Apply the full domain adaptation framework | Image dehazing · HazeRD | PSNR: 17.37 -> 18.07 | Improved |
| Apply the full domain adaptation framework | Image dehazing · HazeRD | SSIM: 0.56 -> 0.63 | Improved |
| Add unsupervised loss and real-image training without translation (ablation) | SYN dehazing model · Synthetic domain | PSNR: 25.67 -> 25.75 | Improved |
| Add unsupervised loss and real-image training without translation (ablation) | SYN dehazing model · Synthetic domain | SSIM: 0.8801 -> 0.8699 | Hurt |
| Translate real images to the synthetic domain for training (ablation) | SYN+U dehazing model · Synthetic domain | PSNR: 25.75 -> 25.91 | Improved |
| Translate real images to the synthetic domain for training (ablation) | SYN+U dehazing model · Synthetic domain | SSIM: 0.8699 -> 0.8822 | Improved |
| Add both translators and unsupervised loss (ablation) | Dehazing model · Synthetic domain | PSNR: 25.91 -> 27.76 | Improved |
| Add both translators and unsupervised loss (ablation) | Dehazing model · Synthetic domain | SSIM: 0.8822 -> 0.9284 | Improved |
| Train the real-domain dehazer on synthetic-to-real translated images (ablation) | SYN dehazing model · Real hazy images | visual quality | Improved |
Closest papers by meaning
- CoA: Towards Real Image Dehazing via Compression-and-Adaptation (CVPR 2025 · similarity 0.90)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.89)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.88)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.87)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.87)
- 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.
