Non-Local Recurrent Network for Image Restoration

NeurIPS 2018 Ding LiuBihan WenYuchen FanChen Change LoyThomas S. Huang

Many classic methods have shown non-local self-similarity in natural images to be an effective prior for image restoration. However, it remains unclear and challenging to make use of this intrinsic property via deep networks... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Super-Resolution BSD100 - 4x upscaling NLRN PSNR 27.48 # 19
SSIM 0.7306 # 25
Grayscale Image Denoising BSD200 sigma30 NLRN-MV PSNR 28.2 # 2
Grayscale Image Denoising BSD200 sigma50 NLRN-MV PSNR 25.97 # 2
Grayscale Image Denoising BSD200 sigma70 NLRN-MV PSNR 24.62 # 2
Grayscale Image Denoising BSD68 sigma15 NLRN PSNR 31.88 # 1
Grayscale Image Denoising BSD68 sigma25 NLRN PSNR 29.41 # 1
Grayscale Image Denoising BSD68 sigma50 NLRN PSNR 26.47 # 2
Denoising Darmstadt Noise Dataset NLRN PSNR 30.8 # 8
Grayscale Image Denoising Set12 sigma15 NLRN PSNR 33.16 # 1
Grayscale Image Denoising Set12 sigma30 NLRN PSNR 30.8 # 1
Grayscale Image Denoising Set12 sigma50 NLRN PSNR 27.64 # 2
Image Super-Resolution Set14 - 4x upscaling NLRN PSNR 28.36 # 22
SSIM 0.7745 # 27
Image Super-Resolution Set5 - 4x upscaling NLRN PSNR 31.92 # 19
SSIM 0.8916 # 21
Image Super-Resolution Urban100 - 4x upscaling NLRN PSNR 25.79 # 21
SSIM 0.7729 # 20
Grayscale Image Denoising Urban100 sigma15 NLRN PSNR 33.45 # 2
Grayscale Image Denoising Urban100 sigma25 NLRN PSNR 30.94 # 2
Grayscale Image Denoising Urban100 sigma50 NLRN PSNR 27.49 # 1