Research map / Image generation / Image restoration
Towards Domain Invariant Single Image Dehazing
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 |
|---|---|---|---|
| Train on aggregated real and synthetic datasets rather than a single source dataset | Proposed dehazing model · NTIRE-19 and NTIRE-20 | PSNR: 3.78 db and 6.84db over DuRN-US | Helped |
| Train on aggregated real and synthetic datasets rather than a single source dataset | Proposed dehazing model · SOTS-IN and SOTS-OUT | PSNR | Mixed |
| Add greedy localized data augmentation to the UNet baseline (ablation) | UNet dehazing model · SOTS-IN | PSNR: 18.08 -> 21.53 | Helped |
| Add greedy localized data augmentation to the UNet baseline (ablation) | UNet dehazing model · NTIRE-19 | PSNR: 11.05 -> 15.32 | Helped |
| Add SACA to the GLDA configuration (ablation) | UNet dehazing model · SOTS-IN | SSIM: 0.74 -> 0.82 | Helped |
| Add SACA to the GLDA configuration (ablation) | UNet dehazing model · NTIRE-19 | SSIM: 0.53 -> 0.59 | Helped |
| Add multi-scale feature aggregation to the SACA configuration (ablation) | UNet dehazing model · SOTS-IN | PSNR: 22.07 -> 26.75 | Helped |
| Add multi-scale feature aggregation to the SACA configuration (ablation) | UNet dehazing model · NTIRE-19 | PSNR: 16.70 -> 17.18 | Helped |
| Add a simple discriminator (ablation) | UNet with GLDA, SACA, and MSFA · SOTS-IN | PSNR: 26.75 -> 28.52 | Helped |
| Add a simple discriminator (ablation) | UNet with GLDA, SACA, and MSFA · NTIRE-19 | PSNR: 17.18 -> 17.72 | Helped |
| Use an HF-prior discriminator instead of a simple discriminator (ablation) | UNet with GLDA, SACA, and MSFA · SOTS-IN | SSIM: 0.89 -> 0.94 | Helped |
| Add an LF-prior discriminator alongside the HF-prior discriminator (ablation) | UNet with GLDA, SACA, and MSFA · SOTS-IN | PSNR: 32.87 -> 38.91 | Helped |
Closest papers by meaning
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.90)
- 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 0.89)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.88)
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.88)
- Guided Real Image Dehazing Using YCbCr Color Space (AAAI 2025 · similarity 0.88)
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.