Multiple Reference Views for Hole Reduction in DIBR View Synthesis

被引:0
|
作者
Zhu, Ce [1 ]
Li, Shuai [1 ]
机构
[1] Univ Elect Sci & Technol China, Sch Elect Engn, Chengdu 610054, Peoples R China
来源
2014 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB) | 2014年
关键词
3-D and multi-view video; Video coding and processing; Depth-image-based rendering; view synthesis; hole filling; VIDEO;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Depth-image-based rendering (DIBR) technique is widely used to synthesize virtual views in many applications including multiview and free viewpoint video systems. An inherent problem of DIBR oriented view synthesis is that holes may appear in the synthesized view. Hole filling techniques generally extrapolates/interpolates the hole regions with the neighboring information based on an assumption that the texture pattern in the hole regions is similar to that of the neighboring background information. However, in some cases especially with complex texture, the assumption may not hold. Moreover, hole filling techniques can only provide an estimation for the hole regions which may not be true. In this paper, based on a thorough examination of the hole generation mechanism in view interpolation with multiple reference views, the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views. Furthermore, a scheme of selective warping of the complementary views is developed by efficiently locating a small number of useful pixels in the complementary views for hole reduction. Experimental results show that the hole size based on two primary reference views may be reduced by about 90 percent with the help of complementary reference views, while the developed selective warping scheme can save about 69 percent of rendering time compared with fully warping two complementary reference views in the rendering process.
引用
收藏
页数:5
相关论文
共 50 条
  • [41] Multiple view semi-supervised dimensionality reduction
    Hou, Chenping
    Zhang, Changshui
    Wu, Yi
    Nie, Feiping
    PATTERN RECOGNITION, 2010, 43 (03) : 720 - 730
  • [42] IMPROVED VIEW SYNTHESIS BY MOTION WARPING AND TEMPORAL HOLE FILLING
    Purica, Andrei I.
    Mora, Elie G.
    Pesquet-Popescu, Beatrice
    Cagnazzo, Marco
    Ionescu, Bogdan
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 1191 - 1195
  • [43] Fast MRF-Based Hole Filling for View Synthesis
    Luo, Guibo
    Zhu, Yuesheng
    Guo, Biao
    IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (01) : 75 - 79
  • [44] Fast Hole Filling for View Synthesis in Free Viewpoint Video
    Huang, Hui-Yu
    Huang, Shao-Yu
    ELECTRONICS, 2020, 9 (06) : 909
  • [45] On the Supernatural and Extraordinary Experience: Multiple Views and a Call for Synthesis
    Shanafelt, Robert
    REVIEWS IN ANTHROPOLOGY, 2011, 40 (04) : 312 - 335
  • [46] Real-time view synthesis from a sparse set of views
    Chen, George
    Liu, Yang
    Max, Nelson
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2007, 22 (02) : 188 - 202
  • [47] Virtual view synthesis for the nonuniform illuminated between views in surgical video
    Jia, Boqi
    Zhang, Nan
    Liang, Nan
    Wang, Shiqi
    Wu, Bo
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (13) : 20619 - 20639
  • [48] Virtual view synthesis for the nonuniform illuminated between views in surgical video
    Boqi Jia
    Nan Zhang
    Nan Liang
    Shiqi Wang
    Bo Wu
    Multimedia Tools and Applications, 2021, 80 : 20619 - 20639
  • [49] Robust multi-view feature matching from multiple unordered views
    Yao, Jian
    Cham, Wai-Kuen
    PATTERN RECOGNITION, 2007, 40 (11) : 3081 - 3099
  • [50] Multi-View Modeling in SysML: Thematic Structuring for Multiple Thematic Views
    Munker, Florian
    Albers, Albert
    Wagner, Daniel
    Behrendt, Matthias
    2014 CONFERENCE ON SYSTEMS ENGINEERING RESEARCH, 2014, 28 : 531 - 538