SOTAVerified

Scale-recurrent Network for Deep Image Deblurring

2018-02-06CVPR 2018Code Available0· sign in to hype

Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

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. Compared with the many recent learning-based approaches in [25], it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
GoProSRNSSIM0.93Unverified
HIDE (trained on GOPRO)SRNPSNR (sRGB)28.36Unverified
RealBlur-JSRNPSNR (sRGB)31.38Unverified
RealBlur-J (trained on GoPro)SRNPSNR (sRGB)28.56Unverified
RealBlur-RSRNPSNR (sRGB)38.65Unverified
RealBlur-R (trained on GoPro)SRNSSIM (sRGB)0.95Unverified
RSBlurSRN-DeblurAverage PSNR32.53Unverified

Reproductions