AI Paper Atlas

Research map / Image generation / Image restoration

Residual Dense Network for Image Restoration

Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, Yun Fu

TPAMI 2020 · Image generation › Image restoration · approach: Priors for restoration networks · 928 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 contiguous memory (CM) (ablation)RDN baseline · Set5 x2PSNR: 34.87 -> 37.89Improved
add local residual learning (LRL) (ablation)RDN baseline · Set5 x2PSNR: 34.87 -> 37.92Improved
add global feature fusion (GFF) (ablation)RDN baseline · Set5 x2PSNR: 34.87 -> 37.78Improved
add LRL and GFF to CM (ablation)RDN · Set5 x2PSNR: 37.89 -> 38.06Improved
add GFF to CM+LRL (ablation)RDN · Set5 x2PSNR: 37.99 -> 38.06Improved
add local residual learning (ablation)RDN · Set5 x4PSNR: 32.54 -> 32.61Improved
add local residual learning (ablation)RDN · Urban100 x4PSNR: 26.72 -> 26.85Improved
contiguous memory instead of dense connections (ablation)RDN · Set5 x4PSNR: 32.02 -> 32.61Improved
contiguous memory instead of MemNet connections (ablation)RDN · Urban100 x4PSNR: 25.50 -> 26.85Improved
larger D or C (more RDBs or conv layers) (ablation)RDN · Set5 x2PSNRImproved
larger growth rate G (ablation)RDN · Set5 x2PSNRImproved
self-ensemble test (RDN+) (ablation)RDN · Urban100 x4PSNR: 26.85 -> 27.01Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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