AI Paper Atlas

Research map / Image generation / Image restoration

Unpaired Deep Image Dehazing Using Contrastive Disentanglement Learning

Xiang Chen, Zhentao Fan, Pengpeng Li, Longgang Dai, Caihua Kong, Zhuoran Zheng, Yufeng Huang, Yufeng Li

ECCV 2022 · Image generation › Image restoration · approach: Dehazing and deraining · 63 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 adversarial contrastive loss with negative generators (vs conventional contrastive loss) (ablation)CDD-GAN · Foggy CityscapesPSNR: 19.88 -> 20.35Improved
add adversarial contrastive loss with negative generators (vs conventional contrastive loss) (ablation)CDD-GAN · Foggy CityscapesSSIM: 0.846 -> 0.843No clear effect
add a contrastive loss to the CycleGAN baseline (ablation)CycleGAN baseline · Foggy CityscapesPSNR: 18.64 -> 19.88Improved
add diversity loss L_div (ablation)CDD-GAN with L_ac · Foggy CityscapesPSNR: 20.35 -> 20.71Improved
add diversity loss L_div (ablation)CDD-GAN with L_ac · Foggy CityscapesSSIM: 0.843 -> 0.865Improved
add total variation loss L_tv (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 20.71 / 0.865 -> 20.79 / 0.871Improved
add dark channel loss L_dc (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 20.79 / 0.871 -> 20.93 / 0.874Improved
add dual learning setting S_dual (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 20.72 / 0.863 -> 20.93 / 0.874Improved
increase number of negatives from 64 to 256 (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 19.84 / 0.859 -> 20.93 / 0.874Improved
increase number of negatives from 128 to 256 (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 20.52 / 0.868 -> 20.93 / 0.874Improved
increase number of negatives from 256 to 512 (ablation)CDD-GAN · Foggy CityscapesPSNR / SSIM: 20.93 / 0.874 -> 20.85 / 0.876No clear effect
use CDD-GAN dehazed output as preprocessing for YOLOv3 detectionCDD-GAN · RTTS (100 images)mAP (%): 61.35 -> 66.04Improved

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