Real-Time Light Field Video Focusing and GPU Accelerated Streaming

被引:3
|
作者
Chlubna, Tomas [1 ]
Milet, Tomas [1 ]
Zemcik, Pavel [1 ]
Kula, Michal [1 ]
机构
[1] Brno Univ Technol, Fac Informat Technol, Dept Comp Graph & Multimedia, Bozetechova 2, Brno 61200, Czech Republic
关键词
Light field; GPU; Image-based rendering; DEPTH; RECONSTRUCTION;
D O I
10.1007/s11265-023-01874-8
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes a novel solution of real-time depth range and correct focusing estimation in light field videos represented by arrays of video sequences. This solution, compared to previous approaches, offers a novel way to render high-quality synthetic views from light field videos on contemporary hardware in real-time. Only the video frames containing color information with no other attributes, such as captured depth, are needed. The drawbacks of the previous proposals such as block artifacts in the defocused parts of the scene or manual setting of the depth range are also solved in this paper. This paper describes a complete solution that solves the main memory and performance issues of light field rendering on contemporary personal computers. The whole integration of high-quality light field videos supersedes the approaches in previous works and the paper also provides measurements and experimental results. While reaching the same quality as slower state-of-the-art approaches, this method can still be used in real-time which makes it suitable for industry and real-life scenarios as an alternative to standard 3D rendering approaches.
引用
下载
收藏
页码:703 / 719
页数:17
相关论文
共 50 条
  • [1] Real-Time Light Field Video Focusing and GPU Accelerated Streaming
    Tomáš Chlubna
    Tomáš Milet
    Pavel Zemčík
    Michal Kula
    Journal of Signal Processing Systems, 2023, 95 : 703 - 719
  • [2] GPU-Accelerated Real-Time Video Background Subtraction
    Boghdady, Ramy
    Salama, Cherif
    Wahba, Ayman
    2015 TENTH INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING & SYSTEMS (ICCES), 2015, : 34 - 39
  • [3] An Embedded GPU Accelerated Hyperspectral Video Classification System in Real-Time
    Sancho, Jaime
    Villa, Manuel
    Urbanos, Gemma
    Villanueva, Marta
    Sutradhar, Pallab
    Rosa, Gonzalo
    Martin, Alberto
    Vazquez, Guillermo
    Chavarrias, Miguel
    Salvador, Ruben
    Lagares, Alfonso
    Juarez, Eduardo
    Sanz, Cesar
    2021 XXXVI CONFERENCE ON DESIGN OF CIRCUITS AND INTEGRATED SYSTEMS (DCIS21), 2021, : 131 - 136
  • [4] Accelerated MIPI CSI video stream acquision in tasks of real-time video streaming
    Khodniev, T. A.
    Holub, M. S.
    Kuzhylnyi, O., V
    Lysenko, O. M.
    Varfolomieiev, A. Y.
    VISNYK NTUU KPI SERIIA-RADIOTEKHNIKA RADIOAPARATOBUDUVANNIA, 2020, (82): : 35 - 43
  • [5] Architectures and Codecs for Real-Time Light Field Streaming
    Kovacs, Peter Tamas
    Zare, Alireza
    Balogh, Tibor
    Bregovic, Robert
    Gotchev, Atanas
    JOURNAL OF IMAGING SCIENCE AND TECHNOLOGY, 2017, 61 (01)
  • [6] GPU-Accelerated Foreground Segmentation and Labeling for Real-Time Video Surveillance
    Song, Wei
    Tian, Yifei
    Fong, Simon
    Cho, Kyungeun
    Wang, Wei
    Zhang, Weiqiang
    SUSTAINABILITY, 2016, 8 (10)
  • [7] Real-time stereoscopic video streaming
    McMenemy, K
    Ferguson, S
    DR DOBBS JOURNAL, 2006, 31 (03): : 18 - +
  • [8] Real-time stereoscopic video streaming
    Intelligent Systems and Control Group, Queen's University, Belfast
    不详
    Dr Dobb's J, 2006, 3 (18-22):
  • [9] GPU-accelerated depth codec for real-time, high-quality light field reconstruction
    Koniaris, Babis
    Kosek, Maggie
    Sinclair, David
    Mitchell, Kenny
    PROCEEDINGS OF THE ACM ON COMPUTER GRAPHICS AND INTERACTIVE TECHNIQUES, 2018, 1 (01)
  • [10] A GPU-Accelerated Real-Time NLMeans Algorithm for Denoising Color Video Sequences
    Goossens, Bart
    Luong, Hiep
    Aelterman, Jan
    Pizurica, Aleksandra
    Philips, Wilfried
    ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, PT II, 2010, 6475 : 46 - 57