AI Paper Atlas

Research map / Image generation / Image restoration

Cross-Patch Graph Convolutional Network for Image Denoising

Yao Li, Xueyang Fu, Zheng-Jun Zha

ICCV 2021 · Image generation › Image restoration · approach: Self-supervised image denoising · 25 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
add Cross-Patch GCN (ablation)CPNet · SIDDPSNR: 37.34 -> 38.34Improved
add Cross-Patch GCN (ablation)CPNet · SIDDSSIM: 0.9311 -> 0.9571Improved
add NLF loss (ablation)CPNet · SIDDPSNR: 38.15 -> 38.34Improved
add NLF loss (ablation)CPNet · SIDDSSIM: 0.9531 -> 0.9571Improved
add synthetic-noise data augmentation from DIV2K (ablation)CPNet · SIDDPSNR: 37.61 -> 38.34Improved
add synthetic-noise data augmentation from DIV2K (ablation)CPNet · SIDDSSIM: 0.9382 -> 0.9571Improved
add all three components (CPGCN, NLF loss, augmentation) to baseline (ablation)CPNet · SIDDPSNR: 36.85 -> 38.34Improved
CPNet instead of CycleISPCPNet · SIDDPSNR: 38.13 -> 38.34Improved
CPNet instead of CycleISPCPNet · DNDPSNR: 39.56 -> 39.78Improved
CPNet instead of CycleISPCPNet · DNDSSIM: 0.9564 -> 0.9566No clear effect

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