AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing

Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chia-Wen Lin

ICCV 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 8 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
add PHATNet-generated fine-tuning dataFocalNet · Setting1 averagePSNR (dB): 16.25 -> 17.07Improved
add PHATNet-generated fine-tuning dataSGDN · Setting1 averagePSNR (dB): 14.84 -> 16.77Improved
add PHATNet-generated fine-tuning dataMITNet · Setting2 averagePSNR (dB): 12.44 -> 15.79Improved
add PHATNet-generated fine-tuning dataSGDN · Setting2 averagePSNR (dB): 12.99 -> 16.17Improved
add PHATNet-generated fine-tuning dataDehamer · Setting2 NH-Haze21SSIM: 0.748 -> 0.747No clear effect
add PHATNet-generated fine-tuning dataFocalNet · Setting1 DenseHazeSSIM: 0.434 -> 0.423Hurt
add PHATNet-generated fine-tuning dataSGDN · RTTS (source NH-Haze20)BRISQUE: 34.27 -> 22.21Improved
add PHATNet-generated fine-tuning dataFocalNet · RTTS (source NH-Haze20)NIQE: 4.19 -> 3.92Improved
add both ALE and TME encoders instead of ALE only (ablation)PHATNet · Setting1 average, FocalNetPSNR (dB): 16.46 -> 17.07Improved
add both ALE and TME encoders instead of TME only (ablation)PHATNet · Setting1 average, FocalNetPSNR (dB): 16.80 -> 17.07Improved
use ASM-guided ALE+TME fusion instead of feature concatenation (ablation)PHATNet · Setting1 average, FocalNetPSNR (dB): 16.62 -> 17.07Improved
increase PHDT stages from 1 to 3 (ablation)PHATNet · Setting1 average, FocalNetPSNR (dB): 16.68 -> 17.07Improved

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