CNN-Optimized image compression with uncertainty based resource allocation

Zhenzhong CHEN; Yiming LI; Feiyang LIU; Zizheng LIU; Xiang PAN; Wanjie SUN; Yingbin WANG; Yan ZHOU; Han ZHU; Shan LIU

CNN-Optimized image compression with uncertainty based resource allocation

Zhenzhong CHEN^*
, Yiming LI
, Feiyang LIU
, Zizheng LIU
, Xiang PAN
, Wanjie SUN
, Yingbin WANG
, Yan ZHOU
, Han ZHU
, Shan LIU

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

7 Citations (Scopus)

Abstract

In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. Two solutions were submitted, i.e., “iipTiramisu” and its speedup version “iipTiramisuS”, resulting in 32.14 dB and 32.06 dB in PSNR, respectively. These two results have been ranked No. 1 and 2 on the leaderboard.

Original language	English
Title of host publication	Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Publisher	IEEE
Pages	2559-2562
Number of pages	4
Publication status	Published - 2018
Externally published	Yes
Event	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 - Salt Lake City, United States Duration: 18 Jun 2018 → 22 Jun 2018

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher	IEEE Computer Society
ISSN (Print)	2160-7508

Conference

Conference	31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018
Country/Territory	United States
City	Salt Lake City
Period	18/06/18 → 22/06/18

Bibliographical note

Publisher Copyright:
© 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

Access to Document

https://openaccess.thecvf.com/content_cvpr_2018_workshops/w50/html/Chen_CNN-Optimized_Image_Compression_CVPR_2018_paper.htmlLicence: Unspecified

Cite this

CHEN, Z., LI, Y., LIU, F., LIU, Z., PAN, X., SUN, W., WANG, Y., ZHOU, Y., ZHU, H., & LIU, S. (2018). CNN-Optimized image compression with uncertainty based resource allocation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (pp. 2559-2562). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE. https://openaccess.thecvf.com/content_cvpr_2018_workshops/w50/html/Chen_CNN-Optimized_Image_Compression_CVPR_2018_paper.html

@inproceedings{e347e1cf3748498fa5fc26dcd922d3d5,

title = "CNN-Optimized image compression with uncertainty based resource allocation",

abstract = "In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. Two solutions were submitted, i.e., “iipTiramisu” and its speedup version “iipTiramisuS”, resulting in 32.14 dB and 32.06 dB in PSNR, respectively. These two results have been ranked No. 1 and 2 on the leaderboard.",

author = "Zhenzhong CHEN and Yiming LI and Feiyang LIU and Zizheng LIU and Xiang PAN and Wanjie SUN and Yingbin WANG and Yan ZHOU and Han ZHU and Shan LIU",

note = "Publisher Copyright: {\textcopyright} 2019 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018 ; Conference date: 18-06-2018 Through 22-06-2018",

year = "2018",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE",

pages = "2559--2562",

booktitle = "Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops",

}

CHEN, Z, LI, Y, LIU, F, LIU, Z, PAN, X, SUN, W, WANG, Y, ZHOU, Y, ZHU, H & LIU, S 2018, CNN-Optimized image compression with uncertainty based resource allocation. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE, pp. 2559-2562, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, United States, 18/06/18. <https://openaccess.thecvf.com/content_cvpr_2018_workshops/w50/html/Chen_CNN-Optimized_Image_Compression_CVPR_2018_paper.html>

CNN-Optimized image compression with uncertainty based resource allocation. / CHEN, Zhenzhong; LI, Yiming; LIU, Feiyang et al.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. IEEE, 2018. p. 2559-2562 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - CNN-Optimized image compression with uncertainty based resource allocation

AU - CHEN, Zhenzhong

AU - LI, Yiming

AU - LIU, Feiyang

AU - LIU, Zizheng

AU - PAN, Xiang

AU - SUN, Wanjie

AU - WANG, Yingbin

AU - ZHOU, Yan

AU - ZHU, Han

AU - LIU, Shan

PY - 2018

Y1 - 2018

N2 - In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. Two solutions were submitted, i.e., “iipTiramisu” and its speedup version “iipTiramisuS”, resulting in 32.14 dB and 32.06 dB in PSNR, respectively. These two results have been ranked No. 1 and 2 on the leaderboard.

AB - In this paper, we provide the description of our approach designed for participating the CVPR 2018 Challenge on Learned Image Compression (CLIC). Our approach is a hybrid image coder based on CNN-optimized in-loop filter and mode coding, with uncertainty based resource allocation for compressing the task images. Two solutions were submitted, i.e., “iipTiramisu” and its speedup version “iipTiramisuS”, resulting in 32.14 dB and 32.06 dB in PSNR, respectively. These two results have been ranked No. 1 and 2 on the leaderboard.

UR - https://www.scopus.com/pages/publications/85082584017

M3 - Conference paper (refereed)

AN - SCOPUS:85082584017

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 2559

EP - 2562

BT - Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

PB - IEEE

T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018

Y2 - 18 June 2018 through 22 June 2018

ER -

CNN-Optimized image compression with uncertainty based resource allocation

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this