Papers › Learning Deep CNN Denoiser Prior for Image Restoration

Learning Deep CNN Denoiser Prior for Image Restoration

11 Apr 2017CVPR 2017 7arXiv:1704.03264archive 2025-07-28

Kai Zhang, WangMeng Zuo, Shuhang Gu, Lei Zhang

Model-based optimization methods and discriminative learning methods have been the two dominant strategies for solving various inverse problems in low-level vision. Typically, those two kinds of methods have their respective merits and drawbacks, e.g., model-based optimization methods are flexible for handling different inverse problems but are usually time-consuming with sophisticated priors for the purpose of good performance; in the meanwhile, discriminative learning methods have fast testing speed but their application range is greatly restricted by the specialized task. Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e.g., deblurring). Such an integration induces considerable advantage when the denoiser is obtained via discriminative learning. However, the study of integration with fast discriminative denoiser prior is still lacking. To this end, this paper aims to train a set of fast and effective CNN (convolutional neural network) denoisers and integrate them into model-based optimization method to solve other inverse problems. Experimental results demonstrate that the learned set of denoisers not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.

PaperPDFConference PDFCode

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

Code

cszn/ircnn officialmentioned in paperpytorch 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 DenoisingDeblurringDenoisingImage DenoisingImage Restoration

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Color Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 33.86 #2 of 4 Archive leaderboard report
Color Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 31.16 #3 of 4 Archive leaderboard report
Color Image Denoising BSD68 sigma35 Deep CNN Denoiser PSNR 29.5 #1 of 1 Archive leaderboard report
Color Image Denoising BSD68 sigma5 Deep CNN Denoiser PSNR 40.36 #1 of 1 Archive leaderboard report
Color Image Denoising CBSD68 sigma50 IRCNN PSNR 27.86 #14 of 18 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 31.63 #12 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 29.15 #13 of 16 Archive leaderboard report
Grayscale Image Denoising BSD68 sigma50 Deep CNN Denoiser PSNR 26.19 #14 of 15 Archive leaderboard report
Image Super-Resolution Set14 - 2x upscaling Deep CNN Denoiser PSNR 30.79 #35 of 35 Archive leaderboard report
Image Super-Resolution Set14 - 3x upscaling Deep CNN Denoiser PSNR 27.72 #24 of 24 Archive leaderboard report
Image Super-Resolution Set14 - 4x upscaling Deep CNN Denoiser PSNR 27.59 #91 of 104 Archive leaderboard report
Image Super-Resolution Set5 - 2x upscaling Deep CNN Denoiser PSNR 35.05 #41 of 41 Archive leaderboard report
Image Super-Resolution Set5 - 3x upscaling Deep CNN Denoiser PSNR 31.26 #31 of 32 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

SPEED

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