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
来源
2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2010年
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
  • [41] A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization
    Dai, Yuchao
    Li, Hongdong
    He, Mingyi
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2014, 107 (02) : 101 - 122
  • [42] A Closed-Form, Pairwise Solution to Local Non-Rigid Structure-From-Motion
    Parashar, Shaifali
    Long, Yuxuan
    Salzmann, Mathieu
    Fua, Pascal
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (11) : 7027 - 7040
  • [43] Deep Spatial-Temporal Neural Network for Dense Non-Rigid Structure from Motion
    Wang, Yaming
    Wang, Minjie
    Huang, Wenqing
    Ye, Xiaoping
    Jiang, Mingfeng
    MATHEMATICS, 2022, 10 (20)
  • [44] A Simple Prior-free Method for Non-Rigid Structure-from-Motion Factorization
    Dai, Yuchao
    Li, Hongdong
    He, Mingyi
    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 2018 - 2025
  • [45] Deep Non-Rigid Structure-From-Motion: A Sequence-to-Sequence Translation Perspective
    Deng, Hui
    Zhang, Tong
    Dai, Yuchao
    Shi, Jiawei
    Zhong, Yiran
    Li, Hongdong
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2024, 46 (12) : 10814 - 10828
  • [46] Non-Rigid Shape From Water
    Kuo, Meng-Yu Jennifer
    Kawahara, Ryo
    Nobuhara, Shohei
    Nishino, Ko
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (07) : 2220 - 2232
  • [47] Minimal Basis Subspace Representation: A Unified Framework for Rigid and Non-rigid Motion Segmentation
    Lee, Choon-Meng
    Cheong, Loong-Fah
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017, 121 (02) : 209 - 233
  • [48] Non-rigid metric reconstruction from perspective cameras
    Llado, Xavier
    Del Bue, Alessio
    Agapito, Lourdes
    IMAGE AND VISION COMPUTING, 2010, 28 (09) : 1339 - 1353
  • [49] Recovery of piece-wise planar and piece-wise rigid models from non-rigid motion
    Alon, J
    Sclaroff, S
    THREE-DIMENSIONAL IMAGING, OPTICAL METROLOGY, AND INSPECTION V, 1999, 3835 : 72 - 83
  • [50] 3D NON-RIGID STRUCTURE FROM MOTION BASED ON SPARSE APPROXIMATION IN TRAJECTORY SPACE
    Wang, Yaming
    Yan, Xiaomeng
    Jiang, Mingfeng
    Zheng, Junbao
    INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION, 2018, 33 (02) : 111 - 117