Papers › Residual Dense Network for Image Restoration

Residual Dense Network for Image Restoration

25 Dec 2018arXiv:1812.10477archive 2025-07-28

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

Convolutional neural network has recently achieved great success for image restoration (IR) and also offered hierarchical features. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in IR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional layers. RDB further allows direct connections from the state of preceding RDB to all the layers of current RDB, leading to a contiguous memory mechanism. To adaptively learn more effective features from preceding and current local features and stabilize the training of wider network, we proposed local feature fusion in RDB. After fully obtaining dense local features, we use global feature fusion to jointly and adaptively learn global hierarchical features in a holistic way. We demonstrate the effectiveness of RDN with several representative IR applications, single image super-resolution, Gaussian image denoising, image compression artifact reduction, and image deblurring. Experiments on benchmark and real-world datasets show that our RDN achieves favorable performance against state-of-the-art methods for each IR task quantitatively and visually.

PaperPDFCode

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

Code

yulunzhang/RDN officialmentioned in papermentioned on GitHubpytorch report
QLinhHub/Image-super-resolution mentioned on GitHubtf 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

DeblurringDenoisingImage CompressionImage Compression Artifact ReductionImage DeblurringImage DenoisingImage RestorationImage Super-ResolutionJPEG Artifact CorrectionSuper-Resolution

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising BSD68 sigma10 Residual Dense Network + PSNR 36.49 #1 of 1 Archive leaderboard report
Color Image Denoising BSD68 sigma30 Residual Dense Network + PSNR 30.7 #1 of 1 Archive leaderboard report
Color Image Denoising BSD68 sigma70 Residual Dense Network + PSNR 26.88 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak24 sigma10 Residual Dense Network + PSNR 37.33 #1 of 1 Archive leaderboard report
Color Image Denoising Kodak24 sigma30 Residual Dense Network + PSNR 31.98 #1 of 2 Archive leaderboard report
Color Image Denoising Kodak24 sigma50 Residual Dense Network + PSNR 29.7 #7 of 9 Archive leaderboard report
Color Image Denoising Kodak24 sigma70 Residual Dense Network + PSNR 28.24 #1 of 1 Archive leaderboard report
Color Image Denoising Urban100 sigma10 Residual Dense Network + PSNR 36.75 #1 of 2 Archive leaderboard report
Color Image Denoising Urban100 sigma30 Residual Dense Network + PSNR 31.78 #2 of 2 Archive leaderboard report
Color Image Denoising Urban100 sigma50 Residual Dense Network + PSNR 29.38 #9 of 9 Archive leaderboard report
Color Image Denoising Urban100 sigma70 Residual Dense Network + PSNR 27.74 #1 of 1 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma10 Residual Dense Network + PSNR 34.01 #1 of 2 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma30 Residual Dense Network + PSNR 28.58 #1 of 2 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma50 Residual Dense Network + PSNR 26.43 #7 of 15 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma70 Residual Dense Network + PSNR 25.12 #2 of 3 Archive leaderboard report
Grayscale Image Denoising Kodak24 sigma10 Residual Dense Network + PSNR 35.19 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Kodak24 sigma30 Residual Dense Network + PSNR 30.02 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Kodak24 sigma50 Residual Dense Network + PSNR 27.88 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Kodak24 sigma70 Residual Dense Network + PSNR 26.57 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma10 Residual Dense Network + PSNR 35.45 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma30 Residual Dense Network + PSNR 30.08 #1 of 1 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma50 Residual Dense Network + PSNR 27.47 #7 of 10 Archive leaderboard report
Grayscale Image Denoising Urban100 sigma70 Residual Dense Network + PSNR 25.71 #1 of 2 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 10 Grayscale) Residual Dense Network + PSNR 30.03 #3 of 7 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 10 Grayscale) Residual Dense Network + SSIM 0.8194 #3 of 7 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 20 Grayscale) Residual Dense Network + PSNR 32.19 #3 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 20 Grayscale) Residual Dense Network + SSIM 0.8704 #3 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 30 Grayscale) Residual Dense Network + PSNR 33.46 #3 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 30 Grayscale) Residual Dense Network + SSIM 0.8932 #3 of 6 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 40 Grayscale) Residual Dense Network + PSNR 34.29 #3 of 5 Archive leaderboard report
JPEG Artifact Correction Classic5 (Quality 40 Grayscale) Residual Dense Network + SSIM 0.9063 #3 of 5 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) Residual Dense Network + PSNR 32.1 #3 of 12 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 20 Grayscale) Residual Dense Network + SSIM 0.8886 #3 of 12 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 30 Grayscale) Residual Dense Network + PSNR 33.54 #3 of 7 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 30 Grayscale) Residual Dense Network + SSIM 0.9156 #3 of 7 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 40 Grayscale) Residual Dense Network + PSNR 34.54 #2 of 5 Archive leaderboard report
JPEG Artifact Correction LIVE1 (Quality 40 Grayscale) Residual Dense Network + SSIM 0.9304 #2 of 5 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) Residual Dense Network + PSNR 29.7 #4 of 13 Archive leaderboard report
JPEG Artifact Correction Live1 (Quality 10 Grayscale) Residual Dense Network + SSIM 0.8252 #4 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

Batch NormalizationConcatenated Skip ConnectionConvolutionDense BlockReLU

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