AI Paper Atlas

Research map / Image generation / Image restoration

MemNet: A Persistent Memory Network for Image Restoration

Ying Tai, Jian Yang, Xiaoming Liu, Chunyan Xu

ICCV 2017 · Image generation › Image restoration · approach: Priors for restoration networks · 1,962 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 long-term dense connections among memory blocks (ablation)MemNet · Set5 x2 SISRPSNR (dB): 37.68 -> 37.78Improved
add long-term dense connections among memory blocks (ablation)MemNet · Set5 x3 SISRPSNR (dB): 33.96 -> 34.09Improved
add long-term dense connections among memory blocks (ablation)MemNet · Set5 x4 SISRPSNR (dB): 31.60 -> 31.74Improved
add short-term connections from first R-1 recursions to gate unit (ablation)MemNet · Set5 x2 SISRPSNR (dB): 37.71 -> 37.78Improved
add short-term connections from first R-1 recursions to gate unit (ablation)MemNet · Set5 x3 SISRPSNR (dB): 34.00 -> 34.09Improved
add short-term connections from first R-1 recursions to gate unit (ablation)MemNet · Set5 x4 SISRPSNR (dB): 31.65 -> 31.74Improved
increase depth from M4R6 (54 layers) to M6R6 (80 layers) (ablation)MemNet · Set5 x3 SISRPSNR (dB): 34.05 -> 34.09Improved
increase depth from M6R6 (80 layers) to M6R8 (104 layers) (ablation)MemNet · Set5 x3 SISRPSNR (dB): 34.09 -> 34.16Improved
increase depth from M6R6 (80 layers) to M10R10 (212 layers) (ablation)MemNet · Set5 x3 SISRPSNR (dB): 34.09 -> 34.23Improved
use MemNet instead of RED for denoisingMemNet vs RED · BSD200 sigma=70PSNR (dB): 24.37 -> 24.53Improved
use MemNet instead of DnCNN for JPEG deblockingMemNet vs DnCNN · Classic5 q=10PSNR (dB): 29.40 -> 29.69Improved
use MemNet instead of DRRN for SISRMemNet vs DRRN · Urban100 x4PSNR (dB): 25.44 -> 25.50Improved

Later papers that compared with this method

9 later accepted papers report MemNet as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.

1 more not listed.

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