Research map / Image generation / Image restoration
HNDiff: Haze-Noise Diffusion for Image Dehazing
Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng, Min-Hung Chen, Chia-Wen Lin, Yen-Yu Lin
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 HNDiff latent prior | FocalNet/ConvIR/SGDN · six dehazing benchmarks | PSNR: avg +0.57 dB PSNR, +0.009 SSIM | Improved |
| add HNDiff to RIDCP | RIDCP · RTTS | FADE/NIMA/BRISQUE: FADE 0.944 -> 0.417; NIMA 4.43 -> 5.08; BRISQUE 18.78 -> 16.09 | Improved |
| add haze diffusion (ablation) | FocalNet · NH-HAZE | PSNR: 20.36 -> 20.61 | Improved |
| add noise diffusion (ablation) | FocalNet · NH-HAZE | PSNR: 20.36 -> 20.46 | Improved |
| add haze-aware noise scheduler (HANS) (ablation) | FocalNet+HNDiff · NH-HAZE | PSNR: 20.68 -> 20.89 | Improved |
| use HNDiff instead of DDPM/RDDM prior (ablation) | FocalNet · NH-HAZE | PSNR: DDPM 20.46, RDDM 20.43 -> 20.89 | Improved |
| use standard diffusion prior instead of U-Net (ablation) | FocalNet · NH-HAZE | PSNR: U-Net 20.41 vs DDPM 20.46 vs RDDM 20.43 | No clear effect |
| enlarge baseline to match params (ablation) | FocalNet · NH-HAZE | PSNR: 20.36 -> 20.37 (wider), 20.51 (deeper) | No clear effect |
| apply diffusion in latent instead of image space (ablation) | FocalNet+HNDiff · RW2AH | PSNR: 21.37 -> 21.52; FLOPs 65.59G -> 36.38G | Improved |
| increase diffusion steps beyond 4 (6 for ConvIR) (ablation) | HNDiff · NH-HAZE/O-HAZE | PSNR | No clear effect |
| add HNDiff overhead | FocalNet · training cost | Params/FLOPs: Params 3.74M -> 7.82M; FLOPs 30.53G -> 36.38G | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RIDCP — RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors (CVPR 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.91)
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing (NeurIPS 2026 · similarity 0.90)
- BlurDM: A Blur Diffusion Model for Image Deblurring (NeurIPS 2025 · similarity 0.87)
- Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models (ICLR 2025 · similarity 0.87)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.87)
- NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation (ICLR 2024 · 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.
