Learning Deep CNN Denoiser Prior for Image Restoration

CVPR 2017  ·  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. read more

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Grayscale Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 31.63 # 6
Color Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 33.86 # 2
Grayscale Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 29.15 # 9
Color Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 31.16 # 3
Color Image Denoising BSD68 sigma35 Deep CNN Denoiser PSNR 29.5 # 1
Color Image Denoising BSD68 sigma5 Deep CNN Denoiser PSNR 40.36 # 1
Grayscale Image Denoising BSD68 sigma50 Deep CNN Denoiser PSNR 26.19 # 10
Color Image Denoising CBSD68 sigma50 IRCNN PSNR 27.86 # 6
Image Super-Resolution Set14 - 2x upscaling Deep CNN Denoiser PSNR 30.79 # 19
Image Super-Resolution Set14 - 3x upscaling Deep CNN Denoiser PSNR 27.72 # 11
Image Super-Resolution Set14 - 4x upscaling Deep CNN Denoiser PSNR 27.59 # 48
Image Super-Resolution Set5 - 2x upscaling Deep CNN Denoiser PSNR 35.05 # 23
Image Super-Resolution Set5 - 3x upscaling Deep CNN Denoiser PSNR 31.26 # 15
Image Super-Resolution Set5 - 4x upscaling Deep CNN Denoiser PSNR 30.92 # 49

Methods


No methods listed for this paper. Add relevant methods here