Learning Deep CNN Denoiser Prior for Image Restoration

CVPR 2017 Kai ZhangWangmeng ZuoShuhang GuLei 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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Grayscale Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 31.63 # 5
Color Image Denoising BSD68 sigma15 Deep CNN Denoiser PSNR 33.86 # 2
Color Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 31.16 # 3
Grayscale Image Denoising BSD68 sigma25 Deep CNN Denoiser PSNR 29.15 # 7
Color Image Denoising BSD68 sigma35 Deep CNN Denoiser PSNR 29.5 # 1
Color Image Denoising BSD68 sigma5 Deep CNN Denoiser PSNR 40.36 # 1
Color Image Denoising BSD68 sigma50 Deep CNN Denoiser PSNR 27.86 # 4
Grayscale Image Denoising BSD68 sigma50 Deep CNN Denoiser PSNR 26.19 # 9
Image Super-Resolution Set14 - 2x upscaling Deep CNN Denoiser PSNR 30.79 # 15
Image Super-Resolution Set14 - 3x upscaling Deep CNN Denoiser PSNR 27.72 # 9
Image Super-Resolution Set14 - 4x upscaling Deep CNN Denoiser PSNR 27.59 # 40
Image Super-Resolution Set5 - 2x upscaling Deep CNN Denoiser PSNR 35.05 # 17
Image Super-Resolution Set5 - 3x upscaling Deep CNN Denoiser PSNR 31.26 # 13
Image Super-Resolution Set5 - 4x upscaling Deep CNN Denoiser PSNR 30.92 # 33