On Versatile Video Coding at UHD with Machine-Learning-Based Super-Resolution

被引:4
|
作者
Fischer, Kristian [1 ]
Herglotz, Christian [1 ]
Kaup, Andre [1 ]
机构
[1] Friedrich Alexander Univ Erlangen Nurnberg FAU, Multimedia Commun & Signal Proc, Cauerstr 7, D-91058 Erlangen, Germany
关键词
VVC; video compression; CNN super-resolution; 4K/UHD video; spatial-resolution scaling; VDSR; RDN;
D O I
10.1109/qomex48832.2020.9123140
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing. We propose a coding chain with spatial down- and upscaling that combines the next-generation VVC codec with machine learning based single image super-resolution algorithms for 4K. The investigated coding chain, which spatially downscales the 4K data before coding, shows superior quality than the conventional VVC reference software for low bitrate scenarios. Throughout several tests, we find that up to 12 % and 18 % Bjontegaard delta rate gains can be achieved on average when coding 4K sequences with VVC and QP values above 34 and 42, respectively. Additionally, the investigated scenario with up- and downscaling helps to reduce the loss of details and compression artifacts, as it is shown in a visual example.
引用
收藏
页数:6
相关论文
共 50 条
  • [31] An Adaptive Down-Sampling Based Video Coding with Hybrid Super-Resolution Method
    Hu, Zeng
    Li, Houqiang
    Li, Weiping
    [J]. 2012 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 2012), 2012, : 504 - 507
  • [32] Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
    Fukami, Kai
    Fukagata, Koji
    Taira, Kunihiko
    [J]. JOURNAL OF FLUID MECHANICS, 2021, 909
  • [33] Efficient multiple-example based super-resolution for symmetric mixed resolution stereoscopic video coding
    Chung, Kuo-Liang
    Huang, Yong-Huai
    [J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2016, 39 : 65 - 81
  • [34] Single Image Super-resolution Based on Residual Learning and Convolutional Sparse Coding
    Xie, Chao
    Jiang, Shengqin
    Lu, Xiaobo
    [J]. TENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2018), 2018, 10806
  • [35] UHD Video Coding: A Light-Weight Learning-Based Fast Super-Block Approach
    Wang, Miaohui
    Xie, Wuyuan
    Meng, Xiandong
    Zeng, Huanqiang
    Ngan, King Ngi
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2019, 29 (10) : 3083 - 3094
  • [36] Super-Resolution Meets Machine Learning: Approximation of Measures
    Mhaskar, H. N.
    [J]. JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2019, 25 (06) : 3104 - 3122
  • [37] Super-Resolution Meets Machine Learning: Approximation of Measures
    H. N. Mhaskar
    [J]. Journal of Fourier Analysis and Applications, 2019, 25 : 3104 - 3122
  • [38] Super-resolution reconstruction of turbulent flows with machine learning
    Fukami, Kai
    Fukagata, Koji
    Taira, Kunihiko
    [J]. JOURNAL OF FLUID MECHANICS, 2019, 870 : 106 - 120
  • [39] Conditional Neural Video Coding with Spatial-Temporal Super-Resolution
    Wang, Henan
    Pan, Xiaohan
    Feng, Runsen
    Guo, Zongyu
    Chen, Zhibo
    [J]. 2024 DATA COMPRESSION CONFERENCE, DCC, 2024, : 591 - 591
  • [40] Machine learning assisted quantum super-resolution microscopy
    Kudyshev, Zhaxylyk A.
    Sychev, Demid
    Martin, Zachariah
    Bogdanov, Simeon, I
    Xu, Xiaohui
    Kildishev, Alexander, V
    Boltasseva, Alexandra
    Shalaev, Vladimir M.
    [J]. 2021 CONFERENCE ON LASERS AND ELECTRO-OPTICS (CLEO), 2021,