Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review

45 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherIEEE
Pages6969-6977
ISBN (Electronic)978-1-5386-0457-1
ISBN (Print)9781538604588
Publication statusPublished - Jul 2017

Conference

Title30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
PlaceUnited States
CityHonolulu
Period21 - 26 July 2017

Abstract

In this paper, we propose a fully convolutional network for iterative non-blind deconvolution. We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noise in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.

Citation Format(s)

Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution. / Zhang, Jiawei; Pan, Jinshan; Lai, Wei-Sheng; Lau, Rynson W.H.; Yang, Ming-Hsuan.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. IEEE, 2017. p. 6969-6977.

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)peer-review