AI Paper Atlas

Research map / Image generation / Image restoration

Controlling the Rain: From Removal to Rendering

Siqi Ni, Xueyun Cao, Tao Yue, Xuemei Hu

CVPR 2021 · Image generation › Image restoration · approach: Reflection removal · 41 citations (OpenAlex)

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 RICNet for derainingRainLevel5 · RainLevel5PSNR: 35.99 -> 37.81Improved
Use RICNet for derainingRain12000 · Rain12000PSNR: 32.39 -> 32.67Improved
Use RICNet for derainingRain800 · Rain800PSNR: 27.50 -> 27.11Hurt
Use RICNet for derainingRain200H · Rain200HPSNR: 28.82 -> 28.84Improved
Use RICNet for derainingSPAData · SPADataPSNR: 41.47 -> 37.98Hurt
Remove NBM (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 5.132Hurt
Use only high-level interpolation (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 4.974Hurt
Use only low-level interpolation (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 4.955Hurt
Remove HOG loss (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 5.612Hurt
Remove autocorrelation loss (ablation)RICNet rain rendering · Rain renderingFSIM: 0.850 -> 0.802Hurt
Use random rather than decremental training (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 4.975Hurt
Use incremental rather than decremental training (ablation)RICNet rain rendering · Rain renderingNIQE: 3.985 -> 5.031Hurt

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