Research map / Image generation / Image restoration
Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing
Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang
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 diffusion model to reconstruct amplitude residuals (ablation) | FrDiff · SOTS-Indoor | PSNR: -2.77 dB without DM | Improved |
| use Amplitude Residual Encoder instead of simple ResBlock (ablation) | FrDiff · SOTS-Indoor | PSNR: -0.31 dB without ARE | Improved |
| add Phase Correction Module (ablation) | FrDiff · SOTS-Indoor | PSNR: -0.29 dB without PCM | Improved |
| introduce amplitude residuals at multiple scales and joint training of DM with dehazing network (ablation) | FrDiff · SOTS-Indoor | PSNR | Improved |
| increase diffusion iteration steps T (ablation) | FrDiff · SOTS-Indoor | PSNR | Improved |
| increase lambda_diff from 0.1 to 10 (ablation) | FrDiff · SOTS-Indoor | PSNR: 36.31 -> 36.54 -> 36.58 | Improved |
| vary lambda_PatchNCE from 0.1 to 10 (ablation) | FrDiff · SOTS-Indoor | PSNR: 36.43 -> 36.54 -> 36.50 | No clear effect |
| frequency-domain diffusion unpaired dehazing vs contrastive-learning methods | FrDiff vs ODCR · SOTS-Indoor | PSNR: 26.32 -> 27.43 | Improved |
| FrDiff on I-HAZE vs D4 | FrDiff · I-HAZE | PSNR: 15.61 (D4) vs 15.35 | 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 2 of 2 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
- Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training (AAAI 2025 · similarity 0.90)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.90)
- FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion (CVPR 2025 · similarity 0.89)
- FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error (CVPR 2025 · similarity 0.88)
- DeblurDiff: Real-Word Image Deblurring with Generative Diffusion Models (NeurIPS 2025 · similarity 0.87)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 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.
