atlas

Research map / Image generation / Image restoration

Singe Image Rain Removal with Unpaired Information: A Differentiable Programming Perspective

AAAI 2019 · Image generation › Image restoration · approach: Dehazing and deraining · 87 citations (OpenAlex)

Read the paperCheck 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
use dense blocks instead of residual blocks in generator (ablation)RR-GAN · Rain800PSNR: 22.82 -> 23.51Helped
use deeply supervised multiscale discriminator instead of last-layer supervision (ablation)RR-GAN · Rain800PSNR: 21.43 -> 23.51Helped
add adversarial loss to MSE reconstruction loss (ablation)RR-GAN · sample imagePSNR: 17.08 -> 23.51Helped
add MSE reconstruction loss to adversarial loss (ablation)RR-GAN · sample imagePSNR: 21.33 -> 23.51Helped
use unpaired instead of paired rain/clean training images (ablation)RR-GAN · Rain100H split 2PSNR: 23.79 -> 23.51Hurt
use attention memory in generator (ablation)RR-GAN generator · qualitative (Fig 3)visual qualityHelped

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