Papers › MemNet: A Persistent Memory Network for Image Restoration

MemNet: A Persistent Memory Network for Image Restoration

7 Aug 2017ICCV 2017 10arXiv:1708.02209archive 2025-07-28

Ying Tai, Jian Yang, Xiaoming Liu, Chunyan Xu

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep persistent memory network (MemNet) that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process. The recursive unit learns multi-level representations of the current state under different receptive fields. The representations and the outputs from the previous memory blocks are concatenated and sent to the gate unit, which adaptively controls how much of the previous states should be reserved, and decides how much of the current state should be stored. We apply MemNet to three image restoration tasks, i.e., image denosing, super-resolution and JPEG deblocking. Comprehensive experiments demonstrate the necessity of the MemNet and its unanimous superiority on all three tasks over the state of the arts. Code is available at https://github.com/tyshiwo/MemNet.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tyshiwo/MemNet officialmentioned in papertf report
rshwndsz/denoiser mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Color Image DenoisingImage RestorationImage Super-ResolutionJPEG Artifact CorrectionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising CBSD68 sigma50 MemNet PSNR 26.33 #18 of 18 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling MemNet PSNR 27.40 #45 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling MemNet SSIM 0.7281 #45 of 71 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling MemNet PSNR 29.42 #41 of 50 Archive leaderboard report
Image Super-Resolution Manga109 - 4x upscaling MemNet SSIM 0.8942 #41 of 50 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling MemNet PSNR 28.26 #75 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling MemNet SSIM 0.7723 #75 of 104 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling MemNet PSNR 25.50 #51 of 65 Archive leaderboard report
Image Super-Resolution Urban100 - 4x upscaling MemNet SSIM 0.7630 #51 of 65 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 10 Grayscale) MemNet PSNR 29.69 #6 of 7 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 10 Color) MemNet PSNR 27.33 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 10 Color) MemNet PSNR-B 27.34 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 10 Color) MemNet SSIM 0.810 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Color) MemNet PSNR 29.76 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Color) MemNet PSNR-B 29.75 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Color) MemNet SSIM 0.877 #7 of 9 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) MemNet PSNR 31.83 #8 of 12 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) MemNet PSNR-B 31.74 #8 of 12 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) MemNet SSIM 0.8970 #8 of 12 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) MemNet PSNR 29.45 #7 of 13 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) MemNet PSNR-B 29.39 #7 of 13 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) MemNet SSIM 0.8327 #7 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Memory Network

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections