Deep non-blind deconvolution via generalized low-rank approximation

Wenqi Ren, Jiawei Zhang, Lin Ma, Jinshan Pan, Xiaochun Cao, Wangmeng Zuo, Wei Liu, Ming Hsuan Yang

Research output: Contribution to journalConference article

5 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)297-307
Number of pages11
JournalAdvances in Neural Information Processing Systems
Volume2018-December
Publication statusPublished - 2018 Jan 1
Event32nd Conference on Neural Information Processing Systems, NeurIPS 2018 - Montreal, Canada
Duration: 2018 Dec 22018 Dec 8

Fingerprint

Deconvolution
Pixels
Neural networks
Degradation

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Ren, W., Zhang, J., Ma, L., Pan, J., Cao, X., Zuo, W., ... Yang, M. H. (2018). Deep non-blind deconvolution via generalized low-rank approximation. Advances in Neural Information Processing Systems, 2018-December, 297-307.
Ren, Wenqi ; Zhang, Jiawei ; Ma, Lin ; Pan, Jinshan ; Cao, Xiaochun ; Zuo, Wangmeng ; Liu, Wei ; Yang, Ming Hsuan. / Deep non-blind deconvolution via generalized low-rank approximation. In: Advances in Neural Information Processing Systems. 2018 ; Vol. 2018-December. pp. 297-307.
@article{2e5f47d282e44801b974b33bbbc2230a,
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.",
author = "Wenqi Ren and Jiawei Zhang and Lin Ma and Jinshan Pan and Xiaochun Cao and Wangmeng Zuo and Wei Liu and Yang, {Ming Hsuan}",
year = "2018",
month = "1",
day = "1",
language = "English",
volume = "2018-December",
pages = "297--307",
journal = "Advances in Neural Information Processing Systems",
issn = "1049-5258",

}

Ren, W, Zhang, J, Ma, L, Pan, J, Cao, X, Zuo, W, Liu, W & Yang, MH 2018, 'Deep non-blind deconvolution via generalized low-rank approximation', Advances in Neural Information Processing Systems, vol. 2018-December, pp. 297-307.

Deep non-blind deconvolution via generalized low-rank approximation. / Ren, Wenqi; Zhang, Jiawei; Ma, Lin; Pan, Jinshan; Cao, Xiaochun; Zuo, Wangmeng; Liu, Wei; Yang, Ming Hsuan.

In: Advances in Neural Information Processing Systems, Vol. 2018-December, 01.01.2018, p. 297-307.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Deep non-blind deconvolution via generalized low-rank approximation

AU - Ren, Wenqi

AU - Zhang, Jiawei

AU - Ma, Lin

AU - Pan, Jinshan

AU - Cao, Xiaochun

AU - Zuo, Wangmeng

AU - Liu, Wei

AU - Yang, Ming Hsuan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85064840487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064840487&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85064840487

VL - 2018-December

SP - 297

EP - 307

JO - Advances in Neural Information Processing Systems

JF - Advances in Neural Information Processing Systems

SN - 1049-5258

ER -

Ren W, Zhang J, Ma L, Pan J, Cao X, Zuo W et al. Deep non-blind deconvolution via generalized low-rank approximation. Advances in Neural Information Processing Systems. 2018 Jan 1;2018-December:297-307.