First Authors | Jacob Kruse |
---|---|
Authors | Jacob Kruse, Carsten Rother, Uwe Schmidt |
Corresponding Authors | |
Last Authors | Uwe Schmidt |
Conference Proceedings Volume Title | 2017 IEEE International Conference on Computer Vision : ICCV 2017 : proceedings : 22-29 October 2017, Venice, Italy |
Series Title | |
Conference Name | 2017 IEEE International Conference on Computer Vision : ICCV 2017 |
Conference Location | Venice, Italy |
Conference Start Date | 2017-10-22 |
Conference End Date | 2017-10-29 |
Chapter Number | |
Publisher | IEEE |
Conference Proceedings Editors | |
ISBN | 978-15386-1032-9 |
First Page | 4596 |
Last Page | 4604 |
Open Access | false |
Print Publication Date | 2017-10-29 |
Online Publication Date | |
Abstract | This work addresses the task of non-blind image deconvolution. Motivated to keep up with the constant increase in image size, with megapixel images becoming the norm, we aim at pushing the limits of efficient FFT-based techniques. Based on an analysis of traditional and more recent learning-based methods, we generalize existing discriminative approaches by using more powerful regularization, based on convolutional neural networks. Additionally, we propose a simple, yet effective, boundary adjustment method that alleviates the problematic circular convolution assumption, which is necessary for FFT-based deconvolution. We evaluate our approach on two common non-blind deconvolution benchmarks and achieve state-of-the-art results even when including methods which are computationally considerably more expensive. |
Cover Image | |
Affiliated With | Myers, Postdocs |
Selected By | |
Acknowledged Services | |
Publication Status | Published |
Edoc Link | |
Sfx Link | |
DOI | 10.1109/ICCV.2017.491 |
PubMed ID | |
WebOfScience Link | |
Alternative Full Text URL | |
Display Publisher Download Only | false |
Visible On MPI-CBG Website | true |
PDF Downloadable | true |
Created By | thuem |
Added Date | 2018-04-05 |
Last Edited By | thuem |
Last Edited Date | 2018-04-05 16:48:33.027 |
Library ID | 7098 |
Document ID | WOS:000425498404070 |
Entry Complete | true |
eDoc Compliant | true |
Include in Edoc Report | true |
In Pure | |
Ready for eDoc Export | |
Author Affiliations Complete | false |
Project Name | |
Project URL | |
Grant ID | |
Funding Programme | |
Funding Organisation |