Occluding Contours for Multi-View Stereo

被引:36
|
作者
Shan, Qi [1 ]
Curless, Brian [1 ]
Furukawa, Yasutaka [2 ]
Hernandez, Carlos [3 ]
Seitz, Steven M. [1 ,3 ]
机构
[1] Univ Washington, Seattle, WA 98195 USA
[2] Washington Univ, St Louis, MO 63130 USA
[3] Google, Mountain View, CA USA
关键词
D O I
10.1109/CVPR.2014.511
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper leverages occluding contours (aka "internal silhouettes") to improve the performance of multi-view stereo methods. The contributions are 1) a new technique to identify free-space regions arising from occluding contours, and 2) a new approach for incorporating the resulting free-space constraints into Poisson surface reconstruction [14]. The proposed approach outperforms state of the art MVS techniques for challenging Internet datasets, yielding dramatic quality improvements both around object contours and in surface detail.
引用
收藏
页码:4002 / 4009
页数:8
相关论文
共 50 条
  • [31] Deep Multi-View Stereo Gone Wild
    Darmon, Francois
    Bascle, Benedicte
    Devaux, Jean-Clement
    Monasse, Pascal
    Aubry, Mathieu
    [J]. 2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021), 2021, : 484 - 493
  • [32] Attention-Aware Multi-View Stereo
    Luo, Keyang
    Guan, Tao
    Ju, Lili
    Wang, Yuesong
    Chen, Zhuo
    Luo, Yawei
    [J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 1587 - 1596
  • [33] Multi-view stereo for community photo collections
    Goesele, Michael
    Snavely, Noah
    Curless, Brian
    Hoppe, Hugues
    Seitz, Steven M.
    [J]. 2007 IEEE 11TH INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS 1-6, 2007, : 825 - +
  • [34] Facetwise Mesh Refinement for Multi-View Stereo
    Romanoni, Andrea
    Matteucci, Matteo
    [J]. 2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 6794 - 6801
  • [35] Shading-Aware Multi-view Stereo
    Langguth, Fabian
    Sunkavalli, Kalyan
    Hadap, Sunil
    Goesele, Michael
    [J]. COMPUTER VISION - ECCV 2016, PT III, 2016, 9907 : 469 - 485
  • [36] PatchmatchNet: Learned Multi-View Patchmatch Stereo
    Wang, Fangjinhua
    Galliani, Silvano
    Vogel, Christoph
    Speciale, Pablo
    Pollefeys, Marc
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 14189 - 14198
  • [37] Multi-View Stereo on Consistent Face Topology
    Fyffe, G.
    Nagano, K.
    Huynh, L.
    Saito, S.
    Busch, J.
    Jones, A.
    Li, H.
    Debevec, P.
    [J]. COMPUTER GRAPHICS FORUM, 2017, 36 (02) : 295 - 309
  • [38] ACCURATE MULTI-VIEW STEREO BY SELECTIVE EXPANSION
    Tian, Hu
    Li, Fei
    [J]. 2017 3DTV CONFERENCE: THE TRUE VISION - CAPTURE, TRANSMISSION AND DISPLAY OF 3D VIDEO (3DTV-CON), 2017,
  • [39] Multi-view Superpixel Stereo in Urban Environments
    Branislav Mičušík
    Jana Košecká
    [J]. International Journal of Computer Vision, 2010, 89 : 106 - 119
  • [40] Handling occlusions in dense Multi-view stereo
    Kang, SB
    Szeliski, R
    Chai, JX
    [J]. 2001 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2001, : 103 - 110