Papers › Real Image Denoising with Feature Attention

Real Image Denoising with Feature Attention

16 Apr 2019ICCV 2019 10arXiv:1904.07396archive 2025-07-28

Saeed Anwar, Nick Barnes

Deep convolutional neural networks perform better on images containing spatially invariant noise (synthetic noise); however, their performance is limited on real-noisy photographs and requires multiple stage network modeling. To advance the practicability of denoising algorithms, this paper proposes a novel single-stage blind real image denoising network (RIDNet) by employing a modular architecture. We use a residual on the residual structure to ease the flow of low-frequency information and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality on three synthetic and four real noisy datasets against 19 state-of-the-art algorithms demonstrate the superiority of our RIDNet.

PaperPDFConference PDFCode

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

Code

saeed-anwar/RIDNet 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 DenoisingDenoisingImage Denoising

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising BSD68 sigma15 RIDNet PSNR 34.01 #1 of 4 Archive leaderboard report
Color Image Denoising BSD68 sigma25 RIDNet PSNR 31.37 #1 of 4 Archive leaderboard report
Color Image Denoising CBSD68 sigma50 RIDNet PSNR 28.14 #9 of 18 Archive leaderboard report
Color Image Denoising Darmstadt Noise Dataset RIDNet (blind) PSNR (sRGB) 39.23 #3 of 6 Archive leaderboard report
Color Image Denoising Darmstadt Noise Dataset RIDNet (blind) SSIM (sRGB) 0.9526 #3 of 6 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma15 RIDNet PSNR 31.81 #9 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma25 RIDNet PSNR 29.34 #7 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma50 RIDNet PSNR 26.4 #8 of 15 Archive leaderboard report
Image Denoising DND RIDNet PSNR (sRGB) 39.26 #15 of 16 Archive leaderboard report
Image Denoising DND RIDNet SSIM (sRGB) 0.953 #15 of 16 Archive leaderboard report
Image Denoising SIDD RIDNet PSNR (sRGB) 38.71 #19 of 22 Archive leaderboard report
Image Denoising SIDD RIDNet SSIM (sRGB) 0.951 #19 of 22 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.

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