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] Shanghai Univ Engn Sci, Sch Urban Rail Transportat, Shanghai 201620, Peoples R China
[2] Shanghai Univ Engn Sci, Artificial Intelligence Ind Res Inst, Shanghai 201620, Peoples R China
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2024年 / E107卷 / 12期
关键词：
end-to-end rate control; DCVC; convolutional neural network; temporal correlation;
D O I：
10.1587/transinf.2024EDL8041
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
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 .1 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.
引用
收藏
页码：1550 / 1553
页数：4
相关论文
共 50 条
  • [41] End-to-end neural network based optimal quadcopter control
    Ferede, Robin
    de Croon, Guido
    De Wagter, Christophe
    Izzo, Dario
    ROBOTICS AND AUTONOMOUS SYSTEMS, 2024, 172
  • [42] Fair end-to-end window-based congestion control
    Mo, JH
    Walrand, J
    IEEE-ACM TRANSACTIONS ON NETWORKING, 2000, 8 (05) : 556 - 567
  • [43] A GMPLS Based Control Plane Testbed For End-to-end Services
    Li, Guangzhi
    Yates, Jennifer
    Wang, Dongmei
    Sebos, Panagiotis
    Gottlieb, Joel
    Greenberg, Albert
    Kalmanek, Charles
    Doverspike, Robert
    2ND INTERNATIONAL CONFERENCE ON BROADBAND NETWORKS (BROADNETS 2005), 2005, : 269 - +
  • [44] Fair end-to-end window-based congestion control
    Mo, J
    Walrand, J
    PERFORMANCE AND CONTROL OF NETWORK SYSTEMS II, 1998, 3530 : 55 - 63
  • [45] End-to-end tomography and congestion control on multicast based videoconferencing
    Zhang, Xuan
    Li, Xing
    Li, Chongrong
    THIRD 2008 INTERNATIONAL CONFERENCE ON CONVERGENCE AND HYBRID INFORMATION TECHNOLOGY, VOL 2, PROCEEDINGS, 2008, : 60 - 65
  • [46] End-to-End Congestion Control for Content-Based Networks
    Malekpour, Amirhossein
    Carzaniga, Antonio
    Pedone, Fernando
    2014 IEEE 33RD INTERNATIONAL SYMPOSIUM ON RELIABLE DISTRIBUTED SYSTEMS (SRDS), 2014, : 221 - 231
  • [47] End-to-end measurement based admission control for VoIP networks
    Mase, K
    Toyama, Y
    2002 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2002, : 1194 - 1198
  • [48] Field trial of end-to-end QoS control based on RACS
    Zhou, Yong
    Xiao, Xiaojun
    Du, Chunsheng
    Zhou, Jing A.
    2006 10TH IEEE SINGAPORE INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS, VOLS 1 AND 2, 2006, : 181 - +
  • [49] An algorithm for optimal flow control based end-to-end multipath
    Xue, Miao
    Dong, Ping
    Zhang, Si-Dong
    Zhang, Hong-Ke
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2012, 40 (03): : 564 - 570
  • [50] Generalized BER based theory and methodology of end-to-end rate control for MANET streaming media transmission
    Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
    不详
    Jisuanji Xuebao, 2007, 7 (1154-1163): : 1154 - 1163
12345