Temporal Correlation-Based End-to-End Rate Control in DCVC

被引：0

作者：

Yang, Zhenglong ^{[1
]}

Deng, Weihao ^{[1
]}

Wang, Guozhong ^{[2
]}

Fan, Tao ^{[2
]}

Luo, Yixi ^{[1
]}

机构：

[1] School of Urban Rail Transportation, Shanghai University of Engineering Science, Shanghai,201620, China

[2] Artificial Intelligence Industry Research Institute, Shanghai University of Engineering Science, Shanghai,201620, China

来源：

IEICE Transactions on Information and Systems | 2024年 / E107.D卷 / 12期

关键词：

Image compression;

D O I：

10.1587/transinf.2024EDL8041

中图分类号：

学科分类号：

摘要：

Recent deep-learning-based video compression models have demonstrated superior performance over traditional codecs. However, few studies have focused on deep learning rate control. In this paper, end-to-end rate control is proposed for deep contextual video compression (DCVC). With the designed two-branch residual-based network, the optimal bit rate ratio is predicted according to the feature correlation of the adjacent frames. Then, the bit rate can be reasonably allocated for every frame by satisfying the temporal feature. To minimize the rate distortion (RD) cost, the optimal λ of the current frame can be obtained from a two-branch regression-based network using the temporal encoded information. The experimental results show that the achievable BD-rate (PSNR) and BD-rate (SSIM) of the proposed algorithm are −0.84% and −0.35%, respectively, with 2.25% rate control accuracy. © 2024 The Institute of Electronics, Information and Communication Engineers.

引用

页码：1550 / 1553

共 50 条

[21] TCP over end-to-end ABR: A study of TCP performance with end-to-end rate control and stochastic available capacity
Shakkottai, S
Kumar, A
GLOBECOM 98: IEEE GLOBECOM 1998 - CONFERENCE RECORD, VOLS 1-6: THE BRIDGE TO GLOBAL INTEGRATION, 1998, : 525 - 532
[22] End-to-end representation learning for Correlation Filter based tracking
Valmadre, Jack
Bertinetto, Luca
Henriques, Joao
Vedaldi, Andrea
Torr, Philip H. S.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5000 - 5008
[23] Design and analysis of queuing delay control for end-to-end rate control algorithm
Chen, JR
Chen, YC
IEICE TRANSACTIONS ON COMMUNICATIONS, 1999, E82B (10) : 1577 - 1585
[24] End-to-end measurement-based admission control
Gao, Wen-Yu
Wang, Jian-Xin
Chen, Song-Qiao
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics, 2007, 29 (08): : 1366 - 1370
[25] An End-to-end Flow Control Method Based on DQN
Gao, Guichao
Jin, Rong
2022 INTERNATIONAL CONFERENCE ON BIG DATA, INFORMATION AND COMPUTER NETWORK (BDICN 2022), 2022, : 504 - 507
[26] ETERCA: An End-to-End Rate Control Algorithm for packet switching networks
Mascolo, S
Grieco, LA
Di Sciascio, E
JOURNAL OF HIGH SPEED NETWORKS, 2004, 13 (01) : 59 - 85
[27] Performance evaluation of an end-to-end rate control approach for ABR services
Natl Chiao Tung Univ, Hsinchu, Taiwan
IEICE Trans Commun, 12 (2400-2412):
[28] Performance evaluation of an end-to-end rate control approach for ABR services
Chen, JR
Chen, YC
Chan, CT
IEICE TRANSACTIONS ON COMMUNICATIONS, 1998, E81B (12) : 2400 - 2412
[29] Improving the Performance of End-to-End Single Rate Multicast Congestion Control
Kammoun, W.
Youssef, H.
2008 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS, VOLS 1-3, 2008, : 881 - 885
[30] RAP: An end-to-end rate-based congestion control mechanism for realtime streams in the Internet
Rejaie, Reza
Handley, Mark
Estrin, Deborah
Proceedings - IEEE INFOCOM, 1999, 3 : 1337 - 1345

← 1 2 3 4 5 →