Deep Video Compression for P-frame in Sub-sampled Color Spaces

Rongqun Lin; Pingping Zhang; Meng Wang; Shiqi Wang; Sam Kwong

doi:10.1109/ISCAS48785.2022.9937560

Deep Video Compression for P-frame in Sub-sampled Color Spaces

Rongqun Lin, Pingping Zhang, Meng Wang, Shiqi Wang, Sam Kwong

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

6 Citations (Scopus)

Abstract

In this paper, we propose a deep video compression method for P-frame in sub-sampled color spaces regarding the YUV420, which has been widely adopted in many state-of-art hybrid video compression standards, in an effort to achieve high compression performance. We adopt motion estimation and motion compression to facilitate the inter prediction of the videos with YUV420 color format, shrinking the total data volume of motion information. Moreover, the motion compensation module on YUV420 is cooperated to enhance the quality of the compensated frame with the consideration of the resolution alignment in the sub-sampled color spaces. To explore the cross-component correlation, the residual encoder-decoder is accompanied with two head-branches and color information fusion. Additionally, a weighted loss emphasizing more on the Y component is utilized to enhance the compression efficiency. Experimental results show that the proposed method can realize 19.82% bit rate reductions on average compared to the deep video compression (DVC) method in terms of the combined PSNR and predominant gains on the Y component.

Original language	English
Title of host publication	2022 IEEE International Symposium on Circuits and Systems (ISCAS)
Publisher	IEEE
Pages	3200-3204
ISBN (Electronic)	9781665484855, 978-1-6654-8484-8
ISBN (Print)	978-1-6654-8486-2
DOIs	https://doi.org/10.1109/ISCAS48785.2022.9937560
Publication status	Published - 2022
Event	55th IEEE International Symposium on Circuits and Systems (ISCAS 2022) - The Austin Hilton (Hybrid), Austin, United States Duration: 28 May 2022 → 1 Jun 2022 https://epapers.org/iscas2022/ESR/session_sched_view.php

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
ISSN (Print)	0271-4310
ISSN (Electronic)	2158-1525

Conference

Conference	55th IEEE International Symposium on Circuits and Systems (ISCAS 2022)
Abbreviated title	IEEE ISCAS 2022
Place	United States
City	Austin
Period	28/05/22 → 1/06/22
Internet address	https://epapers.org/iscas2022/ESR/session_sched_view.php

Research Keywords

Deep learning
learned video compression
P-frame
sub-sampled color spaces

Access Output

10.1109/ISCAS48785.2022.9937560

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{6c62a18c69c14bf1b3a7b9db12f7094b,

title = "Deep Video Compression for P-frame in Sub-sampled Color Spaces",

abstract = "In this paper, we propose a deep video compression method for P-frame in sub-sampled color spaces regarding the YUV420, which has been widely adopted in many state-of-art hybrid video compression standards, in an effort to achieve high compression performance. We adopt motion estimation and motion compression to facilitate the inter prediction of the videos with YUV420 color format, shrinking the total data volume of motion information. Moreover, the motion compensation module on YUV420 is cooperated to enhance the quality of the compensated frame with the consideration of the resolution alignment in the sub-sampled color spaces. To explore the cross-component correlation, the residual encoder-decoder is accompanied with two head-branches and color information fusion. Additionally, a weighted loss emphasizing more on the Y component is utilized to enhance the compression efficiency. Experimental results show that the proposed method can realize 19.82% bit rate reductions on average compared to the deep video compression (DVC) method in terms of the combined PSNR and predominant gains on the Y component.",

keywords = "Deep learning, learned video compression, P-frame, sub-sampled color spaces",

author = "Rongqun Lin and Pingping Zhang and Meng Wang and Shiqi Wang and Sam Kwong",

year = "2022",

doi = "10.1109/ISCAS48785.2022.9937560",

language = "English",

isbn = "978-1-6654-8486-2",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "IEEE",

pages = "3200--3204",

booktitle = "2022 IEEE International Symposium on Circuits and Systems (ISCAS)",

address = "United States",

note = "55th IEEE International Symposium on Circuits and Systems (ISCAS 2022), IEEE ISCAS 2022 ; Conference date: 28-05-2022 Through 01-06-2022",

url = "https://epapers.org/iscas2022/ESR/session_sched_view.php",

}

Lin, R , Zhang, P , Wang, M , Wang, S & Kwong, S 2022, Deep Video Compression for P-frame in Sub-sampled Color Spaces. in 2022 IEEE International Symposium on Circuits and Systems (ISCAS). Proceedings - IEEE International Symposium on Circuits and Systems, IEEE, pp. 3200-3204, 55th IEEE International Symposium on Circuits and Systems (ISCAS 2022), Austin, Texas, United States, 28/05/22. https://doi.org/10.1109/ISCAS48785.2022.9937560

Deep Video Compression for P-frame in Sub-sampled Color Spaces. / Lin, Rongqun ; Zhang, Pingping ; Wang, Meng et al.
2022 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 2022. p. 3200-3204 (Proceedings - IEEE International Symposium on Circuits and Systems).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Deep Video Compression for P-frame in Sub-sampled Color Spaces

AU - Lin, Rongqun

AU - Zhang, Pingping

AU - Wang, Meng

AU - Wang, Shiqi

AU - Kwong, Sam

PY - 2022

Y1 - 2022

N2 - In this paper, we propose a deep video compression method for P-frame in sub-sampled color spaces regarding the YUV420, which has been widely adopted in many state-of-art hybrid video compression standards, in an effort to achieve high compression performance. We adopt motion estimation and motion compression to facilitate the inter prediction of the videos with YUV420 color format, shrinking the total data volume of motion information. Moreover, the motion compensation module on YUV420 is cooperated to enhance the quality of the compensated frame with the consideration of the resolution alignment in the sub-sampled color spaces. To explore the cross-component correlation, the residual encoder-decoder is accompanied with two head-branches and color information fusion. Additionally, a weighted loss emphasizing more on the Y component is utilized to enhance the compression efficiency. Experimental results show that the proposed method can realize 19.82% bit rate reductions on average compared to the deep video compression (DVC) method in terms of the combined PSNR and predominant gains on the Y component.

AB - In this paper, we propose a deep video compression method for P-frame in sub-sampled color spaces regarding the YUV420, which has been widely adopted in many state-of-art hybrid video compression standards, in an effort to achieve high compression performance. We adopt motion estimation and motion compression to facilitate the inter prediction of the videos with YUV420 color format, shrinking the total data volume of motion information. Moreover, the motion compensation module on YUV420 is cooperated to enhance the quality of the compensated frame with the consideration of the resolution alignment in the sub-sampled color spaces. To explore the cross-component correlation, the residual encoder-decoder is accompanied with two head-branches and color information fusion. Additionally, a weighted loss emphasizing more on the Y component is utilized to enhance the compression efficiency. Experimental results show that the proposed method can realize 19.82% bit rate reductions on average compared to the deep video compression (DVC) method in terms of the combined PSNR and predominant gains on the Y component.

KW - Deep learning

KW - learned video compression

KW - P-frame

KW - sub-sampled color spaces

UR - http://www.scopus.com/inward/record.url?scp=85142525935&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85142525935&origin=recordpage

U2 - 10.1109/ISCAS48785.2022.9937560

DO - 10.1109/ISCAS48785.2022.9937560

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-6654-8486-2

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 3200

EP - 3204

BT - 2022 IEEE International Symposium on Circuits and Systems (ISCAS)

PB - IEEE

T2 - 55th IEEE International Symposium on Circuits and Systems (ISCAS 2022)

Y2 - 28 May 2022 through 1 June 2022

ER -

Deep Video Compression for P-frame in Sub-sampled Color Spaces

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this