Zero-Order Reverse Filtering

Xin Tao; Chao Zhou; Xiaoyong Shen; Jue Wang; Jiaya Jia

doi:10.1109/ICCV.2017.33

Zero-Order Reverse Filtering

Xin Tao, Chao Zhou, Xiaoyong Shen, Jue Wang, Jiaya Jia

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

31 Citations (Scopus)

Abstract

In 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.

Original language	English
Title of host publication	Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	222-230
Number of pages	9
ISBN (Electronic)	9781538610329
DOIs	https://doi.org/10.1109/ICCV.2017.33
Publication status	Published - 22 Dec 2017
Externally published	Yes
Event	16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy Duration: 22 Oct 2017 → 29 Oct 2017

Publication series

Name	Proceedings of the IEEE International Conference on Computer Vision
Volume	2017-October
ISSN (Print)	1550-5499

Conference

Conference	16th IEEE International Conference on Computer Vision, ICCV 2017
Country/Territory	Italy
City	Venice
Period	22/10/17 → 29/10/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Access to Document

10.1109/ICCV.2017.33

Cite this

Tao, X., Zhou, C., Shen, X., Wang, J., & Jia, J. (2017). Zero-Order Reverse Filtering. In Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017 (pp. 222-230). Article 8237295 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2017.33

@inproceedings{e662fb1b7a3e4170bebe30243dae6622,

title = "Zero-Order Reverse Filtering",

abstract = "In 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.",

author = "Xin Tao and Chao Zhou and Xiaoyong Shen and Jue Wang and Jiaya Jia",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 16th IEEE International Conference on Computer Vision, ICCV 2017 ; Conference date: 22-10-2017 Through 29-10-2017",

year = "2017",

month = dec,

day = "22",

doi = "10.1109/ICCV.2017.33",

language = "English",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "222--230",

booktitle = "Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017",

}

Tao, X, Zhou, C, Shen, X, Wang, J & Jia, J 2017, Zero-Order Reverse Filtering. in Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017., 8237295, Proceedings of the IEEE International Conference on Computer Vision, vol. 2017-October, Institute of Electrical and Electronics Engineers Inc., pp. 222-230, 16th IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, 22/10/17. https://doi.org/10.1109/ICCV.2017.33

Zero-Order Reverse Filtering. / Tao, Xin; Zhou, Chao; Shen, Xiaoyong et al.
Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 222-230 8237295 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2017-October).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Zero-Order Reverse Filtering

AU - Tao, Xin

AU - Zhou, Chao

AU - Shen, Xiaoyong

AU - Wang, Jue

AU - Jia, Jiaya

PY - 2017/12/22

Y1 - 2017/12/22

N2 - In 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.

AB - In 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.

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000425498400024

UR - https://openalex.org/W2964142300

UR - https://www.scopus.com/pages/publications/85041921568

U2 - 10.1109/ICCV.2017.33

DO - 10.1109/ICCV.2017.33

M3 - Conference Paper published in a book

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 222

EP - 230

BT - Proceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 16th IEEE International Conference on Computer Vision, ICCV 2017

Y2 - 22 October 2017 through 29 October 2017

ER -

Zero-Order Reverse Filtering

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this