NEURAL NETWORK-BASED ERROR CONCEALMENT FOR VVC

被引：5
|
作者：
Benjak, Martin [1 ]
Samayoa, Yasser [1 ]
Ostermann, Joern [1 ]
机构：
[1] Leibniz Univ Hannover, Inst Informat Verarbeitung, D-30167 Hannover, Germany
来源：
2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年
关键词：
VVC; video communication; video coding; error concealment;
D O I：
10.1109/ICIP42928.2021.9506399
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we introduce an error concealment method for VVC based on deep recurrent neural networks, which employs the PredNet model to estimate missing video frames by using past decoded frames. The network is trained using the BVI-DVC data set to infer even full-HD frames. We integrated our proposed model in the VVC reference software VTM for its evaluation. It performs, in average, 6 dB or up to 5 dB better than the frame copy model in terms of PSNR measurements for a concealed I-frame or P-frame, respectively.
引用
收藏
页码：2114 / 2118
页数：5
相关论文
共 50 条
  • [31] Recurrent Neural Network-Based Temperature Control System Weight Pruning Based on Nonlinear Reconstruction Error
    Liu, Yuan
    Kawaguchi, Takahiro
    Xu, Song
    Hashimoto, Seiji
    [J]. PROCESSES, 2022, 10 (01)
  • [32] Distortion-based Neural Network for Compression Artifacts Reduction in VVC
    Qian, Jian
    Wang, Hongkui
    Yu, Li
    [J]. 2021 INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), 2021,
  • [33] VVC In-Loop Filtering Based on Deep Convolutional Neural Network
    Bouaafia, Soulef
    Messaoud, Seifeddine
    Khemiri, Randa
    Sayadi, Fatma Elzahra
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2021, 2021
  • [34] ERROR CONCEALMENT FOR SCALABLE VIDEO CODING BASED ON DEFORMABLE CONVOLUTION NETWORK
    Wang, Zhao
    Yang, YiFeng
    Zhang, Hao
    [J]. 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 2455 - 2459
  • [35] Syntax based error concealment
    Papadakis, V
    Lynch, WE
    Le-Ngoc, T
    [J]. ISCAS '98 - PROCEEDINGS OF THE 1998 INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-6, 1998, : C265 - C268
  • [36] Improved method of deblocking filter based on convolutional neural network in VVC
    Yang, Jing
    Du, Biao
    Tang, Tong
    [J]. 2020 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA (ICCC), 2020, : 764 - 769
  • [37] VVC In-Loop Filtering Based on Deep Convolutional Neural Network
    Bouaafia, Soulef
    Messaoud, Seifeddine
    Khemiri, Randa
    Sayadi, Fatma Elzahra
    [J]. Computational Intelligence and Neuroscience, 2021, 2021
  • [38] Neural Network-Based Real Time PID Gain Update Algorithm for Contour Error Reduction
    Chang Nho Cho
    Young Hun Song
    Chang-Hyuk Lee
    Hong Ju Kim
    [J]. International Journal of Precision Engineering and Manufacturing, 2018, 19 : 1619 - 1625
  • [39] Syntax based error concealment
    Lynch, WE
    Papadakis, V
    Krishnamurthy, R
    LeNgoc, T
    [J]. SIGNAL PROCESSING-IMAGE COMMUNICATION, 2001, 16 (09) : 827 - 835
  • [40] Error concealment based on overlapping
    Kuo, TY
    Tsao, SC
    [J]. VISUAL COMMUNICATIONS AND IMAGE PROCESSING 2002, PTS 1 AND 2, 2002, 4671 : 146 - 153
12345