AI Paper Atlas

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

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
use clean image as input instead of noise concatenation (one-step strategy) (ablation)GenHaze · RTTSFID: 59.04 -> 57.12Improved
use offline haze database embedding instead of hand-crafted prompt (ablation)GenHaze · RTTSFID: 58.58 -> 57.12Improved
add offline haze database (ablation)GenHaze · RTTSFID: 58.05 -> 57.12Improved
add learnable prompt embedding (ablation)GenHaze · RTTSFID: 57.99 -> 57.12Improved
add positional encoding (ablation)GenHaze · RTTSFID: 57.76 -> 57.12Improved
add haze modulation (ablation)GenHaze · RTTSFID: 58.79 -> 57.12Improved
use degradation encoder with haze modulation instead of ControlNet (ablation)GenHaze · RTTSFID: 58.29 -> 57.12Improved
apply haze modulation after each stage instead of decoder only (ablation)GenHaze · RTTSFID: 58.01 -> 57.12Improved
fine-tune with GenHaze haze instead of physical haze (RIDCP)MSBDN · RTTSFADE: 0.8532 -> 0.6881Improved
fine-tune with physical haze (RIDCP) on real-world baselineKANet · RTTSFADE: 0.8705 -> 0.8746Hurt
fine-tune with GenHaze for 1-2 epochsMSBDN · RTTSBRISQUE: 28.51 -> 20.23Improved
fine-tune with GenHaze for 1-2 epochsPSD · RTTSPaQ-2-PiQ: 71.06 -> 70.45Hurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy