Zero-order Reverse Filtering
Refereed conference paper presented and published in conference proceedings


Times Cited
Altmetrics Information
.

Other information
AbstractIn this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters. We broadly define filters as operations to smooth images or to produce layers via global or local algorithms. And we raise the intriguingly problem if they are reservable to the status before filtering. To answer it, we present a novel strategy to understand general filter via contraction mappings on a metric space. A very simple yet effective zero-order algorithm is proposed. It is able to practically reverse most filters with low computational cost. We present quite a few experiments in the paper and supplementary file to thoroughly verify its performance. This method can also be generalized to solve other inverse problems and enables new applications.
All Author(s) ListTao X, Zhou C, Shen XY, Wang J, Jia JY
Name of Conference16th IEEE International Conference on Computer Vision (ICCV)
Start Date of Conference22/10/2017
End Date of Conference29/10/2017
Place of ConferenceVenice, Italy
Country/Region of ConferenceItaly
Journal name2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
Proceedings Title2017 IEEE International Conference on Computer Vision (ICCV)
Title of Publication2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
Year2017
PublisherIEEE
Pages222 - 230
ISBN978-1-5386-1032-9
ISSN1550-5499
LanguagesEnglish-United Kingdom
Web of Science Subject CategoriesComputer Science, Artificial Intelligence;Engineering, Electrical & Electronic;Computer Science;Engineering

Last updated on 2020-06-08 at 03:27