Paper Info
Title
Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation.
Abstract
In this paper, we present a deep convolutional neural network to capture the inherent properties of image degradation, which can handle different kernels and saturated pixels in a unified framework. The proposed neural network is motivated by the low-rank property of pseudo-inverse kernels. Specifically, we first compute a generalized low-rank approximation to a large number of blur kernels, and then use separable filters to initialize the convolutional parameters in the network. Our analysis shows that the estimated decomposed matrices contain the most essential information of an input kernel, which ensures the proposed network to handle various blurs in a unified framework and generate high-quality deblurring results. Experimental results on benchmark datasets with noisy and saturated pixels demonstrate that the proposed deconvolution approach relying on generalized low-rank approximation performs favorably against the state-of-the-arts.
Year
Venue
Keywords
2018
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018)
large number,unified framework,experimental results,low-rank approximation,essential information,deep convolutional neural network
Field
DocType
Volume
Kernel (linear algebra),Mathematical optimization,Blind deconvolution,Deblurring,Convolutional neural network,Matrix (mathematics),Computer science,Algorithm,Low-rank approximation,Pixel,Artificial neural network
Conference
31
ISSN
Citations 
PageRank 
1049-5258
2
0.36
References 
Authors
0
8
Name
Order
Citations
PageRank
Wenqi Ren133527.14
Jiawei Zhang211111.52
Lin Ma391271.35
Jin-shan Pan456730.84
Xiaochun Cao51986131.55
Wangmeng Zuo63833173.11
Wei Liu74041204.19
Yang Ming-Hsuan815303620.69