Research map / Image generation / Text-to-image diffusion
GenHaze: Pioneering Controllable One-Step Realistic Haze Generation for Real-World Dehazing
Sixiang Chen, Tian Ye, Yunlong Lin, Yeying Jin, Yijun Yang, Haoyu Chen, Jianyu Lai, Song Fei, Zhaohu Xing, Fugee Tsung, Lei Zhu
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 |
|---|---|---|---|
| use clean image as input instead of noise concatenation (one-step strategy) (ablation) | GenHaze · RTTS | FID: 59.04 -> 57.12 | Improved |
| use offline haze database embedding instead of hand-crafted prompt (ablation) | GenHaze · RTTS | FID: 58.58 -> 57.12 | Improved |
| add offline haze database (ablation) | GenHaze · RTTS | FID: 58.05 -> 57.12 | Improved |
| add learnable prompt embedding (ablation) | GenHaze · RTTS | FID: 57.99 -> 57.12 | Improved |
| add positional encoding (ablation) | GenHaze · RTTS | FID: 57.76 -> 57.12 | Improved |
| add haze modulation (ablation) | GenHaze · RTTS | FID: 58.79 -> 57.12 | Improved |
| use degradation encoder with haze modulation instead of ControlNet (ablation) | GenHaze · RTTS | FID: 58.29 -> 57.12 | Improved |
| apply haze modulation after each stage instead of decoder only (ablation) | GenHaze · RTTS | FID: 58.01 -> 57.12 | Improved |
| fine-tune with GenHaze haze instead of physical haze (RIDCP) | MSBDN · RTTS | FADE: 0.8532 -> 0.6881 | Improved |
| fine-tune with physical haze (RIDCP) on real-world baseline | KANet · RTTS | FADE: 0.8705 -> 0.8746 | Hurt |
| fine-tune with GenHaze for 1-2 epochs | MSBDN · RTTS | BRISQUE: 28.51 -> 20.23 | Improved |
| fine-tune with GenHaze for 1-2 epochs | PSD · RTTS | PaQ-2-PiQ: 71.06 -> 70.45 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- InstructPix2Pix — InstructPix2Pix: Learning To Follow Image Editing Instructions (CVPR 2023) · better on 2 of 2 shared results
- RIDCP — RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors (CVPR 2023) · better on 1 of 1 shared result
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 0.93)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.89)
- GenDeg: Diffusion-based Degradation Synthesis for Generalizable All-In-One Image Restoration (CVPR 2025 · similarity 0.88)
- Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images (CVPR 2025 · similarity 0.88)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.87)
- Adaptive Dynamic Dehazing via Instruction-Driven and Task-Feedback Closed-Loop Optimization for Diverse Downstream Task Adaptation (AAAI 2026 · 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.
