AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

HazeFlow: Revisit Haze Physical Model as ODE and Non-Homogeneous Haze Generation for Real-World Dehazing

Junseong Shin, Seungwoo Chung, Yunjeong Yang, Tae Hyun Kim

ICCV 2025 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Physics-informed operator learning · 13 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 Reflow stage after pretraining (ablation)HazeFlow · RTTSBRISQUE: 18.96 -> 8.14Improved
add Reflow stage after pretraining (ablation)HazeFlow · RTTSFADE: 0.561 -> 0.598Hurt
add Distillation stage after Reflow (ablation)HazeFlow · RTTSBRISQUE: 8.14 -> 5.01Improved
train with MCBM non-homogeneous haze synthesis instead of prior haze synthesis (ablation)HazeFlow · RTTSFADE: 0.950 -> 0.817Improved
add transmission refinement (T-Refinement) (ablation)HazeFlow · RTTSFADE: 0.817 -> 0.583Improved
add T-Refinement (ablation)HazeFlow · RTTSBRISQUE: 12.67 -> 5.01Improved
use MCBM haze generation to train other dehazing backbones versus RIDCP augmentationDehazeFormer, NAFNet, FocalNet · RTTSFADE: DehazeFormer 1.44 -> 1.05; NAFNet 1.17 -> 1.03; FocalNet 1.36 -> 0.80Improved
use MCBM haze generation instead of RIDCP augmentationNAFNet and FocalNet · RTTSBRISQUE: NAFNet 21.01 -> 23.68; FocalNet 28.07 -> 29.90Mixed
use ASM-derived ODE instead of naive rectified flow linear interpolation (ablation)HazeFlow · RTTSFADE: 1.059 -> 0.583Improved
use one-step flow inference instead of iterative diffusion samplingHazeFlow vs diffusion dehazers · RTTSrun time (s): 38.09 (DACLIP, 100 steps) -> 0.21 (1 step)Improved
increase number of estimation steps at inferenceHazeFlow · RTTSFADE/BRISQUE vs PAQ2PIQMixed
replace DCP with Non-local or DCPDN for initial transmission map (ablation)HazeFlow · RTTSFADE: 0.583 -> 0.734 (Non-local); 0.583 -> 0.713 (DCPDN)Hurt

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