Papers › Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

29 Jun 2016arXiv:1606.08921archive 2025-07-28

Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang

Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers. In other words, the network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers capture the abstraction of image contents while eliminating corruptions. Deconvolutional layers have the capability to upsample the feature maps and recover the image details. To deal with the problem that deeper networks tend to be more difficult to train, we propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains better results.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

17 repositories listed; official and paper-mentioned ones first.

AdneneBoumessouer/Anomaly-Detection mentioned on GitHubtfSyntology: not harvested report
AdneneBoumessouer/LEGO-Anomaly-Detection mentioned on GitHubtfSyntology: not harvested report
AdneneBoumessouer/MVTec-Anomaly-Detection mentioned on GitHubtfSyntology: not harvested report
Georg030/MRI-Image-Denoising mentioned on GitHubtfSyntology: not harvested report
MNaseerSubhani/MVTec-Anomaly-Detection-For-Industry mentioned on GitHubtfSyntology: not harvested report
OlafChrist-github/Image-Denoising-using-Keras mentioned on GitHubSyntology: not harvested report
Shakib-IO/Diminishing_Image_Noise_Using_Deep_Learning mentioned on GitHubSyntology: not harvested report
chintan1995/Image-Denoising-using-Deep-Learning mentioned on GitHubMITSyntology: not harvested report
jupiterman/Super-Resolution-Images mentioned on GitHubtfSyntology: not harvested report
lee-aaron/Image-Super-Resolution mentioned on GitHubtfSyntology: not harvested report
meitalB/NN mentioned on GitHubtfSyntology: not harvested report
miriskalt/AnomalyDetectionAutoencoder mentioned on GitHubtfSyntology: not harvested report
nekitmm/starnet mentioned on GitHubtfSyntology: not harvested report
nunof98/AiVision_Anomaly_Detection mentioned on GitHubtfSyntology: not harvested report
teakkkz/imageSR mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Image Super-Resolution Using Deep Convolutional Networks (arXiv:1501.00092; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 0 violated, 14 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified) and Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (arXiv:1609.04802; that paper's own run record: 55 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 3 violated, 39 with no contract checked; 10 where Syntology's instrument failed) · 17 unverified); nothing checks that they implement this paper's method. report
titu1994/Image-Super-Resolution mentioned on GitHubtfSyntology: not harvested report
ved27/RED-net mentioned on GitHubSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

DenoisingImage DenoisingImage RestorationJPEG Artifact CorrectionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Grayscale Image Denoising BSD200 sigma10 RED30 PSNR 33.63 #2 of 2 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma10 RED30 SSIM 0.9319 #2 of 2 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma30 RED30 PSNR 27.95 #3 of 3 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma30 RED30 SSIM 0.8019 #3 of 3 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma50 RED30 PSNR 25.75 #3 of 3 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma50 RED30 SSIM 0.7167 #3 of 3 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma70 RED30 PSNR 24.37 #3 of 3 Archive leaderboard report
Grayscale Image Denoising BSD200 sigma70 RED30 SSIM 0.6551 #3 of 3 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling RED30 PSNR 31.99 #25 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 2x upscaling RED30 SSIM 0.8974 #25 of 30 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling RED30 PSNR 28.93 #17 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 3x upscaling RED30 SSIM 0.7994 #17 of 21 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling RED30 PSNR 27.4 #44 of 71 Archive leaderboard report
Image Super-Resolution BSD100 - 4x upscaling RED30 SSIM 0.729 #44 of 71 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling RED30 PSNR 32.94 #33 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling RED30 SSIM 0.9144 #33 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling RED30 PSNR 29.61 #22 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling RED30 SSIM 0.8341 #22 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RED30 PSNR 27.86 #84 of 104 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling RED30 SSIM 0.7718 #84 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling RED30 PSNR 37.66 #31 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling RED30 SSIM 0.9599 #31 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling RED30 PSNR 33.82 #28 of 32 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling RED30 SSIM 0.923 #28 of 32 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) RED30 PSNR 31.73 #9 of 12 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) RED30 PSNR 29.35 #10 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

Convolution

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