MAP Visibility Estimation for Large-Scale Dynamic 3D Reconstruction

被引:10
|
作者
Joo, Hanbyul [1 ]
Park, Hyun Soo [1 ]
Sheikh, Yaser [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
关键词
D O I
10.1109/CVPR.2014.147
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many traditional challenges in reconstructing 3D motion, such as matching across wide baselines and handling occlusion, reduce in significance as the number of unique viewpoints increases. However, to obtain this benefit, a new challenge arises: estimating precisely which cameras observe which points at each instant in time. We present a maximum a posteriori (MAP) estimate of the time-varying visibility of the target points to reconstruct the 3D motion of an event from a large number of cameras. Our algorithm takes, as input, camera poses and image sequences, and outputs the time-varying set of the cameras in which a target patch is visibile and its reconstructed trajectory. We model visibility estimation as a MAP estimate by incorporating various cues including photometric consistency, motion consistency, and geometric consistency, in conjunction with a prior that rewards consistent visibilities in proximal cameras. An optimal estimate of visibility is obtained by finding the minimum cut of a capacitated graph over cameras. We demonstrate that our method estimates visibility with greater accuracy, and increases tracking performance producing longer trajectories, at more locations, and at higher accuracies than methods that ignore visibility or use photometric consistency alone.
引用
收藏
页码:1122 / 1129
页数:8
相关论文
共 50 条
  • [1] 3D Laser Omnimapping for 3D Reconstruction of Large-Scale Scenes
    Hu, Shaoxing
    Zhang, Aiwu
    [J]. 2009 JOINT URBAN REMOTE SENSING EVENT, VOLS 1-3, 2009, : 688 - +
  • [2] FREEHAND INTERACTION WITH LARGE-SCALE 3D MAP DATA
    Adhikarla, Vamsi Kiran
    Wozniak, Pawel
    Barsi, Attila
    Singhal, Dave
    Kovacs, Peter Tamas
    Balogh, Tibor
    [J]. 2014 3DTV-CONFERENCE: THE TRUE VISION - CAPTURE, TRANSMISSION AND DISPLAY OF 3D VIDEO (3DTV-CON), 2014,
  • [3] Large-Scale 3D Scene Reconstruction with Hilbert Maps
    Guizilini, Vitor
    Ramos, Fabio
    [J]. 2016 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS 2016), 2016, : 3247 - 3254
  • [4] Large-scale outdoor 3D reconstruction on a mobile device
    Schoeps, Thomas
    Sattler, Torsten
    Hane, Christian
    Pollefeys, Marc
    [J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2017, 157 : 151 - 166
  • [5] Power Bundle Adjustment for Large-Scale 3D Reconstruction
    Weber, Simon
    Demmel, Nikolaus
    Chan, Tin Chon
    Cremers, Daniel
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 281 - 289
  • [6] Representation and Coding of Large-Scale 3D Dynamic Maps
    Cohen, Robert A.
    Tian, Dong
    Krivokuca, Maj A.
    Sugimoto, Kazuo
    Vetro, Anthony
    Wakimoto, Koji
    Sekiguchi, Shunichi
    [J]. APPLICATIONS OF DIGITAL IMAGE PROCESSING XXXIX, 2016, 9971
  • [7] Scanning-based 3D reconstruction of large-scale objects
    Bai, Suqin
    Shi, Jinlong
    Ge, Qijie
    Tian, Zhaohui
    [J]. PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON ROBOTICS, INTELLIGENT CONTROL AND ARTIFICIAL INTELLIGENCE (RICAI 2019), 2019, : 584 - 589
  • [8] Procedure and algorithm of 3D reconstruction of large-scale ancient architecture
    Xia Song
    Zhu Yixuan
    Li Xin
    [J]. THREE-DIMENSIONAL IMAGE CAPTURE AND APPLICATIONS VII, 2006, 6056
  • [9] Large-scale 3D chromatin reconstruction from chromosomal contacts
    Yanlin Zhang
    Weiwei Liu
    Yu Lin
    Yen Kaow Ng
    Shuaicheng Li
    [J]. BMC Genomics, 20
  • [10] Large-scale 3D chromatin reconstruction from chromosomal contacts
    Zhang, Yanlin
    Liu, Weiwei
    Lin, Yu
    Ng, Yen Kaow
    Li, Shuaicheng
    [J]. BMC GENOMICS, 2019, 20 (Suppl 2)