DPICT: Deep Progressive Image Compression Using Trit-Planes

Jae Han Lee; Seungmin Jeon; Kwang Pyo Choi; Youngo Park; Chang Su Kim

doi:10.1109/CVPR52688.2022.01564

DPICT: Deep Progressive Image Compression Using Trit-Planes

Jae Han Lee, Seungmin Jeon, Kwang Pyo Choi, Youngo Park, Chang Su Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

24 Citations (Scopus)

Abstract

We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer tritplanes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.

Original language	English
Title of host publication	Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Publisher	IEEE Computer Society
Pages	16092-16101
Number of pages	10
ISBN (Electronic)	9781665469463
DOIs	https://doi.org/10.1109/CVPR52688.2022.01564
Publication status	Published - 2022
Event	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 - New Orleans, United States Duration: 2022 Jun 19 → 2022 Jun 24

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2022-June
ISSN (Print)	1063-6919

Conference

Conference	2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Country/Territory	United States
City	New Orleans
Period	22/6/19 → 22/6/24

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Low-level vision
Representation learning

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR52688.2022.01564

Cite this

Lee, J. H., Jeon, S., Choi, K. P., Park, Y., & Kim, C. S. (2022). DPICT: Deep Progressive Image Compression Using Trit-Planes. In Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 (pp. 16092-16101). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2022-June). IEEE Computer Society. https://doi.org/10.1109/CVPR52688.2022.01564

DPICT: Deep Progressive Image Compression Using Trit-Planes. / Lee, Jae Han; Jeon, Seungmin; Choi, Kwang Pyo et al.
Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. IEEE Computer Society, 2022. p. 16092-16101 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2022-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, JH, Jeon, S, Choi, KP, Park, Y & Kim, CS 2022, DPICT: Deep Progressive Image Compression Using Trit-Planes. in Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2022-June, IEEE Computer Society, pp. 16092-16101, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, United States, 22/6/19. https://doi.org/10.1109/CVPR52688.2022.01564

Lee JH, Jeon S, Choi KP, Park Y, Kim CS. DPICT: Deep Progressive Image Compression Using Trit-Planes. In Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022. IEEE Computer Society. 2022. p. 16092-16101. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR52688.2022.01564

@inproceedings{9bd1af072a6040f6b7fc19f37f67f26e,

title = "DPICT: Deep Progressive Image Compression Using Trit-Planes",

abstract = "We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer tritplanes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.",

keywords = "Low-level vision, Representation learning",

author = "Lee, {Jae Han} and Seungmin Jeon and Choi, {Kwang Pyo} and Youngo Park and Kim, {Chang Su}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022 ; Conference date: 19-06-2022 Through 24-06-2022",

year = "2022",

doi = "10.1109/CVPR52688.2022.01564",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "16092--16101",

booktitle = "Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022",

}

TY - GEN

T1 - DPICT

T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

AU - Lee, Jae Han

AU - Jeon, Seungmin

AU - Choi, Kwang Pyo

AU - Park, Youngo

AU - Kim, Chang Su

PY - 2022

Y1 - 2022

N2 - We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer tritplanes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.

AB - We propose the deep progressive image compression using trit-planes (DPICT) algorithm, which is the first learning-based codec supporting fine granular scalability (FGS). First, we transform an image into a latent tensor using an analysis network. Then, we represent the latent tensor in ternary digits (trits) and encode it into a compressed bitstream trit-plane by trit-plane in the decreasing order of significance. Moreover, within each trit-plane, we sort the trits according to their rate-distortion priorities and transmit more important information first. Since the compression network is less optimized for the cases of using fewer tritplanes, we develop a postprocessing network for refining reconstructed images at low rates. Experimental results show that DPICT outperforms conventional progressive codecs significantly, while enabling FGS transmission. Codes are available at https://github.com/jaehanlee-mcl/DPICT.

KW - Low-level vision

KW - Representation learning

UR - http://www.scopus.com/inward/record.url?scp=85131926421&partnerID=8YFLogxK

U2 - 10.1109/CVPR52688.2022.01564

DO - 10.1109/CVPR52688.2022.01564

M3 - Conference contribution

AN - SCOPUS:85131926421

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 16092

EP - 16101

BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022

PB - IEEE Computer Society

Y2 - 19 June 2022 through 24 June 2022

ER -

DPICT: Deep Progressive Image Compression Using Trit-Planes

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this