AI Paper Atlas

Research map / Image generation / Image restoration

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Yuntong Ye, Yi Chang, Hanyu Zhou, Luxin Yan

CVPR 2021 · Image generation › Image restoration · approach: Dehazing and deraining · 102 citations (OpenAlex)

Check 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 the background adversarial loss (ablation)JRGR · RainHQPSNR: 27.38 -> 35.59Improved
add the rainy-image adversarial losses (ablation)JRGR · RainHQPSNR: 28.15 -> 35.59Improved
add the cycle-consistency losses (ablation)JRGR · RainHQPSNR: 26.87 -> 35.59Improved
add the MSE loss (ablation)JRGR · RainHQPSNR: 31.24 -> 35.59Improved
pre-train synthetic and real removal subnetworks before joint training (ablation)JRGR · RainHQPSNR: 33.97 -> 35.59Improved
pre-train the real removal subnetwork in addition to synthetic removal pre-training (ablation)JRGR · RainHQPSNR: 34.54 -> 35.59Improved

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