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
来源
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY | 2023年 / 95卷 / 06期
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
收藏
页码:703 / 719
页数:17
相关论文
共 50 条
  • [41] AITransfer: Progressive AI-powered Transmission for Real-Time Point Cloud Video Streaming
    Huang, Yakun
    Zhu, Yuanwei
    Qiao, Xiuquan
    Tan, Zhijie
    Bai, Boyuan
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 3989 - 3997
  • [42] Real-time high definition H.264 video decode using the Xbox 360 GPU
    Carlos, Juan
    Baeza, Arevalo
    Chen, William
    Christoffersen, Eric
    Dinu, Daniel
    Friemel, Barry
    APPLICATIONS OF DIGITAL IMAGE PROCESSING XXX, PTS 1 AND 2, 2007, 6696
  • [43] GPU-based Real-time Face Detector
    Jeong, Jae-chan
    Shin, Ho-chul
    Cho, Jae-il
    2012 9TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAL), 2012, : 173 - 175
  • [44] Real-time massive convolution for audio applications on GPU Massive convolution on GPU
    Belloch, Jose A.
    Gonzalez, Alberto
    Martinez-Zaldivar, F. J.
    Vidal, Antonio M.
    JOURNAL OF SUPERCOMPUTING, 2011, 58 (03) : 449 - 457
  • [45] Real-time Face Detection Algorithm Using GPU
    Feng, Zhongyuan
    Jia, Jinyuan
    Zhao, Feipeng
    2011 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER-AIDED INDUSTRIAL DESIGN & CONCEPTUAL DESIGN, VOLS 1 AND 2: NEW ENGINES FOR INDUSTRIAL DESIGN: INTELLIGENCE - INTERACTION - SERVICES, 2011, : 1284 - 1289
  • [46] A GPU based real-time GPS software receiver
    Thomas Hobiger
    Tadahiro Gotoh
    Jun Amagai
    Yasuhiro Koyama
    Tetsuro Kondo
    GPS Solutions, 2010, 14 : 207 - 216
  • [47] A GPU based real-time GPS software receiver
    Hobiger, Thomas
    Gotoh, Tadahiro
    Amagai, Jun
    Koyama, Yasuhiro
    Kondo, Tetsuro
    GPS SOLUTIONS, 2010, 14 (02) : 207 - 216
  • [48] Real-time 16K video coding on a GPU with complexity scalable BPC-PaCo
    de Cea-Dominguez, Carlos
    Moure, Juan C.
    Bartrina-Rapesta, Joan
    Auli-Llinas, Francesc
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2021, 99
  • [49] Efficient random-access GPU video decoding for light-field rendering
    Chlubna, Tomas
    Milet, Tomas
    Zemcik, Pavel
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2024, 102
  • [50] GPU-Accelerated Real-Time Tracking of Full-Body Motion With Multi-Layer Search
    Zhang, Zheng
    Seah, Hock Soon
    Quah, Chee Kwang
    Sun, Jixiang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2013, 15 (01) : 106 - 119