Virtual view synthesis of people from multiple view video sequences

被引:28
作者
Starck, J [1 ]
Hilton, A [1 ]
机构
[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 7XH, Surrey, England
关键词
view-dependent reconstruction; virtual view rendering; free-viewpoint video; visual reconstruction; image-based rendering;
D O I
10.1016/j.gmod.2005.01.008
中图分类号
TP31 [计算机软件];
学科分类号
081202 [计算机软件与理论]; 0835 [软件工程];
摘要
This paper addresses the synthesis of novel views of people from multiple view video. We consider the target area of the multiple camera 3D Virtual Studio for broadcast production with the requirement for free-viewpoint video synthesis for a virtual camera with the same quality as captured video. A framework is introduced for view-dependent optimisation of reconstructed surface shape to align multiple captured images with sub-pixel accuracy for rendering novel views. View-dependent shape optimisation combines multiple view stereo and silhouette constraints to robustly estimate correspondence between images in the presence of visual ambiguities such as uniform surface regions, self-occlusion, and camera calibration error. Free-viewpoint rendering of video sequences of people achieves a visual quality comparable to the captured video images. Experimental evaluation demonstrates that this approach overcomes limitations of previous stereo- and silhouette-based approaches to rendering novel views of moving people. (c) 2005 Elsevier Inc. All rights reserved.
引用
收藏
页码:600 / 620
页数:21
相关论文
共 33 条
[1]
[Anonymous], P SIGGRAPH
[2]
[Anonymous], 2003, ACM SIGGRAPH
[3]
[Anonymous], 1998, P 25 ANN C COMP GRAP
[4]
Buehler C, 2001, COMP GRAPH, P425, DOI 10.1145/383259.383309
[5]
Debevec P., 1998, 9 EUR REND WORKSH
[6]
Debevec P. E., 1996, Computer Graphics Proceedings. SIGGRAPH '96, P11, DOI 10.1145/237170.237191
[7]
DYER C, 2001, COMPUTATIONAL MODELS, P469
[8]
OBJECT-CENTERED SURFACE RECONSTRUCTION - COMBINING MULTIIMAGE STEREO AND SHADING [J].
FUA, P ;
LECLERC, YG .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 1995, 16 (01) :35-56
[9]
FUSIELLO A, 1997, 8 BRIT MACH VIS C, P400
[10]
Goldluecke B, 2004, PROC CVPR IEEE, P350