Occlusion-aware temporal frame interpolation in a highly scalable video coding setting

被引:2
|
作者
Ruefenacht, Dominic [1 ]
Mathew, Reji [1 ]
Taubman, David [1 ]
机构
[1] Univ New S Wales, Sch EE&T, Sydney, NSW, Australia
关键词
Temporal frame interpolation; Temporal frame upsampling; Geometrically consistent prediction; Occlusion-handling; Motion discontinuity modeling; Bidirectional hierarchical anchoring of motion fields;
D O I
10.1017/ATSIP.2016.8
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We recently proposed a bidirectional hierarchical anchoring (BIHA) of motion fields for highly scalable video coding. The BIHA scheme employs piecewise-smooth motion fields, and uses breakpoints to signal motion discontinuities. In this paper, we show how the fundamental building block of the BIHA scheme can be used to perform bidirectional, occlusion-aware temporal frame interpolation (BOA-TFI). From a "parent" motion field between two reference frames, we use information about motion discontinuities to compose motion fields from both reference frames to the target frame; these then get inverted so that they can be used to predict the target frame. During the motion inversion process, we compute a reliable occlusion mask, which is used to guide the bidirectional motion-compensated prediction of the target frame. The scheme can be used in any state-of-the-art codec, but is most beneficial if used in conjunction with a highly scalable video coder which employs piecewise-smooth motion fields with motion discontinuities. We evaluate the proposed BOA-TFI scheme on a large variety of natural and challenging computer-generated sequences, and our results compare favorably to state-of-the-art TFI methods.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Bidirectional, Occlusion-Aware Temporal Frame Interpolation in a Highly Scalable Video Setting
    Ruefenacht, Dominic
    Mathew, Reji
    Taubman, David
    [J]. 2015 PICTURE CODING SYMPOSIUM (PCS) WITH 2015 PACKET VIDEO WORKSHOP (PV), 2015, : 5 - 9
  • [2] Occlusion-aware Video Temporal Consistency
    Yao, Chun-Han
    Chang, Chia-Yang
    Chien, Shao-Yi
    [J]. PROCEEDINGS OF THE 2017 ACM MULTIMEDIA CONFERENCE (MM'17), 2017, : 777 - 785
  • [3] Occlusion-Aware View Interpolation
    Serdar Ince
    Janusz Konrad
    [J]. EURASIP Journal on Image and Video Processing, 2008
  • [4] Occlusion-Aware View Interpolation
    Ince, Serdar
    Konrad, Janusz
    [J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2008, 2008 (1)
  • [5] Occlusion-Aware Video Object Inpainting
    Ke, Lei
    Tai, Yu-Wing
    Tang, Chi-Keung
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 14448 - 14458
  • [6] Spatio-temporal scalable video coding using subband and adaptive field/frame interpolation
    Yoshida, T
    Sawada, K
    [J]. APCCAS '96 - IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS '96, 1996, : 145 - 148
  • [7] Flow-based frame interpolation networks combined with occlusion-aware mask estimation
    Zhang, Dacheng
    Lei, Weimin
    Zhang, Wei
    Chen, Xinyi
    [J]. IET IMAGE PROCESSING, 2020, 14 (17) : 4579 - 4587
  • [8] Occlusion-Aware Video Registration for Highly Non-Rigid Objects
    Taetz, Bertram
    Bleser, Gabriele
    Golyanik, Vladislav
    Stricker, Didier
    [J]. 2016 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2016), 2016,
  • [9] Learning an Occlusion-Aware Network for Video Deblurring
    Xu, Qian
    Pan, Jinshan
    Qian, Yuntao
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (07) : 4312 - 4323
  • [10] Scalable video coding with adaptive video interpolation
    Bayrakeri, SD
    Mersereau, RM
    [J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 2132 - 2135