AI Paper Atlas

Research map / Image generation / Image restoration

Rethinking Image Deraining via Rain Streaks and Vapors

Yinglong Wang, Yibing Song, Chao Ma, Bing Zeng

ECCV 2020 · Image generation › Image restoration · approach: Dehazing and deraining · 65 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
use pretrained ANet for atmosphere light (ablation)SNet without ANet · Rain-IPSNR: 27.15 -> 27.49Improved
use pretrained ANet for atmosphere light (ablation)SNet without ANet · Rain-IIPSNR: 25.48 -> 28.57Improved
jointly train ANet and SNet (ablation)pretrained ANet + SNet · Rain-IPSNR: 27.49 -> 31.30Improved
jointly train ANet and SNet (ablation)pretrained ANet + SNet · Rain-IIPSNR: 28.57 -> 33.86Improved
add VNet for vapor transmission (ablation)jointly trained SNet+ANet · Rain-IPSNR: 31.30 -> 31.34No clear effect
add VNet for vapor transmission (ablation)jointly trained SNet+ANet · Rain-IIPSNR: 33.86 -> 34.42Improved
add VNet for vapor transmission (ablation)jointly trained SNet+ANet · Rain-ISSIM: 0.897 -> 0.908Improved
add VNet for vapor transmission (ablation)jointly trained SNet+ANet · Rain-IISSIM: 0.930 -> 0.938Improved

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