Non-Rigid Structure from Locally-Rigid Motion

被引:41
|
作者
Taylor, Jonathan [1 ]
Jepson, Allan D. [1 ]
Kutulakos, Kiriakos N. [1 ]
机构
[1] Univ Toronto, Dept Comp Sci, Toronto, ON M5S 1A1, Canada
关键词
STRUCTURE-FROM-MOTION; SHAPE; SURFACES; STREAMS; MODELS; SCENE;
D O I
10.1109/CVPR.2010.5540002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce locally-rigid motion, a general framework for solving the M-point, N-view structure-from-motion problem for unknown bodies deforming under orthography. The key idea is to first solve many local 3-point, N-view rigid problems independently, providing a "soup" of specific, plausibly rigid, 3D triangles. The main advantage here is that the extraction of 3D triangles requires only very weak assumptions: (1) deformations can be locally approximated by near-rigid motion of three points (i.e., stretching not dominant) and (2) local motions involve some generic rotation in depth. Triangles from this soup are then grouped into bodies, and their depth flips and instantaneous relative depths are determined. Results on several sequences, both our own and from related work, suggest these conditions apply in diverse settings-including very challenging ones (e. g., multiple deforming bodies). Our starting point is a novel linear solution to 3-point structure from motion, a problem for which no general algorithms currently exist.
引用
收藏
页码:2761 / 2768
页数:8
相关论文
共 50 条
  • [31] Model Evolution: An Incremental Approach to Non-Rigid Structure from Motion
    Zhu, Shengqi
    Zhang, Li
    Smith, Brandon M.
    2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 1165 - 1172
  • [32] Non-Rigid Structure from Motion through Estimation of Blend Shapes
    Zhang, Peter Boyi
    Hung, Yeung Sam
    2015 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA), 2015, : 567 - 573
  • [33] A scalable, efficient, and accurate solution to non-rigid structure from motion
    Agudo, Antonio
    Moreno-Noguer, Francesc
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2018, 167 : 121 - 133
  • [34] Sequential Non-Rigid Structure from Motion Using Physical Priors
    Agudo, Antonio
    Moreno-Noguer, Francesc
    Calvo, Begona
    Montiel, J. M. M.
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (05) : 979 - 994
  • [35] Incremental perspective motion model for rigid and non-rigid motion separation
    Lai, Tzung-Heng
    Wang, Te-Hsun
    Lien, Jenn-Jier James
    ADVANCES IN IMAGE AND VIDEO TECHNOLOGY, PROCEEDINGS, 2007, 4872 : 613 - 624
  • [36] Local Non-Rigid Structure-from-Motion from Diffeomorphic Mappings
    Parashar, Shaifali
    Salzmann, Mathieu
    Fua, Pascal
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 2056 - 2064
  • [37] Adaptive Non-rigid Registration and Structure from Motion from Image Trajectories
    Del Bue, Alessio
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2013, 103 (02) : 226 - 239
  • [38] Adaptive Non-rigid Registration and Structure from Motion from Image Trajectories
    Alessio Del Bue
    International Journal of Computer Vision, 2013, 103 : 226 - 239
  • [39] Segmentation of rigid motion from non-rigid 2D trajectories
    Del Bue, Alessio
    Llado, Xavier
    Agapito, Lourdes
    PATTERN RECOGNITION AND IMAGE ANALYSIS, PT 1, PROCEEDINGS, 2007, 4477 : 491 - +
  • [40] Correspondence Estimation from Non-Rigid Motion Information
    Wulff, Jonas
    Lotz, Thomas
    Stehle, Thomas
    Aach, Til
    Chase, J. Geoffrey
    MEDICAL IMAGING 2011: IMAGE PROCESSING, 2011, 7962