Scale-recurrent Network for Deep Image Deblurring

被引：1000

作者：

Tao, Xin ^{[1
,2
]}

Gao, Hongyun ^{[1
,2
]}

Shen, Xiaoyong ^{[2
]}

Wang, Jue ^{[3
]}

Jia, Jiaya ^{[1
,2
]}

机构：

[1] Chinese Univ Hong Kong, Hong Kong, Peoples R China

[2] Tencent, YouTu Lab, Shenzhen, Peoples R China

[3] Megvii Inc, Beijing, Peoples R China

来源：

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2018年

关键词：

D O I：

10.1109/CVPR.2018.00853

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 I I. 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.

引用

页码：8174 / 8182

页数：9