AI Paper Atlas

Research map / Image generation / Image restoration

Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining

CVPR 2019 · Image generation › Image restoration · approach: Dehazing and deraining · 346 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 residual learning (RN) to the U-Net base network (ablation)UMRL · Test-1PSNR: 24.25 -> 27.65Helped
Add residual learning (RN) to the U-Net base network (ablation)UMRL · Test-2PSNR: 23.32 -> 25.88Helped
Add the confidence-map network (CN) to BN + RN (ablation)UMRL · Test-1PSNR: 27.65 -> 29.42Helped
Add the confidence-map network (CN) to BN + RN (ablation)UMRL · Test-2PSNR: 25.88 -> 26.47Helped
Add cycle spinning (ablation)UMRL · Test-1PSNR: 29.42 -> 29.77Helped
Add cycle spinning (ablation)UMRL · Test-2PSNR: 26.47 -> 26.67Helped
Add cycle spinning (ablation)DDN · Test-1PSNR: 27.33 -> 27.52Helped
Add cycle spinning (ablation)DDN · Test-2PSNR: 25.63 -> 25.90Helped
Add cycle spinning (ablation)DID-MDN · Test-1PSNR: 27.95 -> 28.19Helped
Add cycle spinning (ablation)DID-MDN · Test-2PSNR: 26.08 -> 26.37Helped

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