Scale-recurrent Network for Deep Image Deblurring

In single image deblurring, the "coarse-to-fine" scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task... (read more)

PDF Abstract CVPR 2018 PDF CVPR 2018 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Deblurring GoPro SRN-Deblur PSNR 30.26 # 14
SSIM 0.9342 # 11
Deblurring HIDE (trained on GOPRO) SRN PSNR (sRGB) 28.36 # 7
SSIM (sRGB) 0.915 # 5
Deblurring RealBlur-J SRN SSIM (sRGB) 0.909 # 2
PSNR (sRGB) 31.38 # 2
Deblurring RealBlur-J (trained on GoPro) SRN PSNR (sRGB) 28.56 # 2
SSIM (sRGB) 0.867 # 2
Deblurring RealBlur-R SRN PSNR (sRGB) 38.65 # 2
SSIM (sRGB) 0.965 # 2
Deblurring RealBlur-R (trained on GoPro) SRN PSNR (sRGB) 35.66 # 3
SSIM (sRGB) 0.947 # 3

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet