Photorealistic scene reconstruction by voxel coloring

被引:326
作者
Seitz, SM [1 ]
Dyer, CR
机构
[1] Carnegie Mellon Univ, Inst Robot, Pittsburgh, PA 15213 USA
[2] Univ Wisconsin, Dept Comp Sci, Madison, WI 53706 USA
基金
美国国家科学基金会;
关键词
scene reconstruction; multi-baseline stereo; invariants; voxel representations; image correspondence; occlusion; photorealism;
D O I
10.1023/A:1008176507526
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A novel scene reconstruction technique is presented, different from previous approaches in its ability to cope with large changes in visibility and its modeling of intrinsic scene color and texture information. The method avoids image correspondence problems by working in a discretized scene space whose voxels are traversed in a fixed visibility ordering. This strategy takes full account of occlusions and allows the input cameras to be far apart and widely distributed about the environment. The algorithm identifies a special set of invariant voxels which together form a spatial and photometric reconstruction of the scene, fully consistent with the input images. The approach is evaluated with images from both inward-facing and outward-facing cameras.
引用
收藏
页码:151 / 173
页数:23
相关论文
共 50 条
  • [1] [Anonymous], SID INT S
  • [2] [Anonymous], P EUR C COMP VIS
  • [3] [Anonymous], P 23 ANN C COMP GRAP
  • [4] [Anonymous], 1992, MATH STAT
  • [5] [Anonymous], P 2 INT C COMP VIS
  • [6] [Anonymous], 1996, LEVEL SET METHODS
  • [7] Novel view synthesis in tensor space
    Avidan, S
    Shashua, A
    [J]. 1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, : 1034 - 1040
  • [8] GENERALIZING EPIPOLAR-PLANE IMAGE-ANALYSIS ON THE SPATIOTEMPORAL SURFACE
    BAKER, HH
    BOLLES, RC
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 1989, 3 (01) : 33 - 49
  • [9] Belhumeur P. N., 1992, Proceedings. 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.92CH3168-2), P506, DOI 10.1109/CVPR.1992.223143
  • [10] Image representations for visual learning
    Beymer, D
    Poggio, T
    [J]. SCIENCE, 1996, 272 (5270) : 1905 - 1909