Basis Constrained 3D Scene Flow on a Dynamic Proxy

被引:0
|
作者
Birkbeck, Neil [1 ]
Cobzas, Dana [1 ]
Jaegersand, Martin [1 ]
机构
[1] Univ Alberta, Edmonton, AB T6G 2M7, Canada
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing scene flow approaches mainly focus on two-frame stereo-pair configurations and reconstruct an image-based representation of scene flow. Instead, we propose a variational formulation of scene flow relative to a coarse proxy geometry, which is better suited for many views. Furthermore, a linear basis is used to represent temporal surface flow, allowing for longer-range temporal correspondence with fewer variables. Our formulation takes known proxy motion into account (e.g, if the proxy is a tracked human subject), which enables 3D trajectory reconstruction when only a single view is available. Additionally, through the appropriate proxy and basis, our framework generalizes existing approaches for scene flow, optic-flow, and two-frame stereo. We illustrate results on real-data for both static and moving proxy surfaces over several frames.
引用
收藏
页码:1967 / 1974
页数:8
相关论文
共 50 条
  • [1] Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction
    Gotardo, Paulo F. U.
    Simon, Tomas
    Sheikh, Yaser
    Matthews, Iain
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 846 - 854
  • [2] Dynamic 3D Scene Reconstruction and Enhancement
    Jiang, Cansen
    Fougerolle, Yohan
    Fofi, David
    Demonceaux, Cedric
    [J]. IMAGE ANALYSIS AND PROCESSING,(ICIAP 2017), PT I, 2017, 10484 : 518 - 529
  • [3] On 3D scene flow and structure estimation
    Zhang, Y
    Kambhamettu, C
    [J]. 2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 2, PROCEEDINGS, 2001, : 778 - 785
  • [4] Unconstrained vs. constrained 3D scene manipulation
    Salzman, T
    Stachniak, S
    Stürzlinger, W
    [J]. ENGINEERING FOR HUMAN-COMPUTER INTERACTION, 2001, 2254 : 207 - 219
  • [5] Dynamic 3D Scene Analysis for Acquiring Articulated Scene Models
    Swadzba, Agnes
    Beuter, Niklas
    Wachsmuth, Sven
    Kummert, Franz
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 2010, : 134 - 141
  • [6] Dynamic 3D Scene Depth Reconstruction via Optical Flow Field Rectification
    Yang, You
    Liu, Qiong
    Ji, Rongrong
    Gao, Yue
    [J]. PLOS ONE, 2012, 7 (11):
  • [7] SFGAN: Unsupervised Generative Adversarial Learning of 3D Scene Flow from the 3D Scene Self
    Wang, Guangming
    Jiang, Chaokang
    Shen, Zehang
    Miao, Yanzi
    Wang, Hesheng
    [J]. ADVANCED INTELLIGENT SYSTEMS, 2022, 4 (04)
  • [8] 3D Scene Flow Estimation with a Piecewise Rigid Scene Model
    Christoph Vogel
    Konrad Schindler
    Stefan Roth
    [J]. International Journal of Computer Vision, 2015, 115 : 1 - 28
  • [9] 3D Scene Flow Estimation with a Piecewise Rigid Scene Model
    Vogel, Christoph
    Schindler, Konrad
    Roth, Stefan
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 115 (01) : 1 - 28
  • [10] Holographic Display of synthetic 3D dynamic scene
    Paturzo, Melania
    Memmolo, Pasquale
    Finizio, Andrea
    Nasanen, Risto
    Naughton, Thomas J.
    Ferraro, Pietro
    [J]. 3D RESEARCH, 2010, 1 (02): : 31 - 35