Please wait a minute...
J4  2014, Vol. 48 Issue (1): 85-91    DOI: 10.3785/j.issn.1008-973X.2014.01.013
    
Multi-view three-dimensional reconstruction using continuous symmetric disparity
ZHU Wen-qiao1, DIAO Chang-yu2, XU Duan-qing1, LU Dong-ming1
1.College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China;
2. Cultural Heritage Institute, Zhejiang University, Hangzhou 310027, China
Download:   PDF(1324KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A robust symmetric continuous disparity based multi-view stereo algorithm was proposed in order to avoid the local optimum caused by the non-convex energy minimization based algorithm. The symmetric continuous method was applied to improve the disparity maps estimated by windows based algorithm. Left and right consistency soft constraint was used for more robust disparity estimation. Neighbor images and disparity maps were further used in order to alleviate the limitation of the continuous method which easily falls into a local minimum. The aforementioned steps were iterated until a high quality disparity map. Simple depth fusion algorithms can be applied because of the quality of the disparity map. The proposed algorithm was tested with both the data sets from Middlebury site and the real world objects, which showed the effectiveness of the algorithm.



Published: 01 January 2014
CLC:  TP 312  
Cite this article:

ZHU Wen-qiao, DIAO Chang-yu, XU Duan-qing, LU Dong-ming. Multi-view three-dimensional reconstruction using continuous symmetric disparity. J4, 2014, 48(1): 85-91.

URL:

http://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2014.01.013     OR     http://www.zjujournals.com/eng/Y2014/V48/I1/85


基于连续对称视差计算的多视图立体匹配

为了解决基于非凸能量最小化的多视图三维重建方法容易陷入到局部解的问题,提出鲁棒的基于连续对称视差的多视图立体匹配算法.采用连续对称优化算法对基于局部窗口的算法产生的视差进行优化,在能量函数中引入左、右一致性约束,为了提升视差图的准确度,采用近邻的图像和视差图迭代地对视差进行改进.每一个视差图对应一个深度图,因为生成的视差图有较好的质量,融合的过程可以采用简单的算法.Middlebury的测试图像和现实中的一些场景的重建的实验效果证明了该算法的有效性.

[1] SEITZ S M, CURLESS B, DIEBEL J, et al. A comparison and evaluation of multi-view stereo reconstruction algorithms [C]∥Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [S.l.]: IEEE, 2006: 519-528.
[2] SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two frame stereo correspondence algorithms [J]. International Journal of Computer Vision, 2001, 47(1/2/3):742.
[3] BROCKERS R. Cooperative stereo matching with color-based adaptive local support [C]∥Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns. Münster: Springer, 2009:1019-1027.
[4] KANADE T, OKUTOMI M. A stereo matching algorithm with an adaptive window: theory and experiment [J]. IEEE TPAMI, 1994, 16(9): 920-932.
[5] KOLMOGOROV V, ZABIH R. Computing visual correspondence with occlusions using graph cuts [C]∥International Conference on Computer Vision.Vancouver:IEEE,2001: 508-515.
[6] SUN Jian, ZHENG Nan-ning, SHUM N Y.Stereo matching using belief propagation [J].IEEE TPAMI, 2003, 25(7):787800.
[7] HAI T, SAWHNEY H S, KUMAR R. A global matching framework for stereo computation [C]∥International Conference on Computer Vision. Vancouver: IEEE, 2001: 532-539.
[8] SUN Jian, LI Yin, BING S, et al. Symmetric stereo matching for occlusion handling [C]∥International Conference on Computer Vision and Pattern Recognition. Washington: IEEE, 2005: 399-406.
[9] STRECHA C, TUYTELAARS T, VAN GOOL L. Dense matching of multiple wide-baseline views [C]∥ International Conference on Computer Vision. Nice: IEEE, 2003: 1194-1201.
[10] 孔相澧,章国峰,华炜. 基于全局优化的保细节分层多视图立体匹配[J]. 计算机辅助设计与图形学学报,2011,23(1):177184.
KONG Xiang-li, ZHANG Guo-feng, HUA wei. Detail preserving hierarchical multi-view stereo matching via global optimization [J]. Journal of Computer-Aided Design and Computer Graphics, 2011, 23(1): 177184.
[11] GEIGER A, ROSER M, URTASUN R. Efficient large-scale stereo matching [C]∥ Asian Conference on Computer Vision. Queenstown: Springer, 2010: 25-38.
[12] LIU Ye-bin, CAO Xun, DAI Qiong-hai, et al. Continuous depth estimation for multi-view stereo [C]∥ Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 2121-2128.
[13] YANG Wen-zhuo, ZHANG Guo-feng, BAO Hu-jun, et al. Consistent depth maps recovery from a trinocular video sequence [C]∥Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012: 1466-1473.
[14] GOESELE M, CURLESS B, SEITZ S M. Multi-view stereo revisited [C]∥International Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2006: 2402-2409.
[15] BRADLEY D, BOUBEKEUR T, HEIDRICH W. Accurate multi-view reconstruction using robust binocular stereo and surface meshing [C]∥ International Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 18.
[16] FURUKAWA Y, PONCE J. Accurate, dense, and robust multi-view stereopsis [J]. IEEE TPAMI, 2010, 32(8): 1362-1376.
[17] LI Jian-guo, LI E, CHEN Yu-rong, et al. Bundled depth-map merging for multi-view stereo [C]∥ Computer Vision and Pattern Recognition. San Francisco: IEEE, 2010: 2769-2776.
[18] ZACH C, POCK T, BISCHOF H. A globally optimal algorithm for robust tv-l1 range image integration [C]∥International Conference on Computer Vision. Rio de Janeiro: IEEE, 2007: 18.
[19] FUSIELLO A, TRUCCO E, VERRI A, et al. A compact algorithm for rectication of stereo pairs [J]. Machine Vision and Applications, 2000, 12(1):16-22.
[20] BROX T, BRUHN A, PAPENBERG N, et al. High accuracy optical flow estimation based on a theory for warping [C]∥ European Conference on Computer Vision. Zofin Palace: Springer, 2004: 25-36.
[21] KAZHDAN M, BOLITHO M, HOPPE H. Poisson surface reconstruction [C]∥ Symposium on Geometry Processing. Cagliari: Eurographics Association, 2006: 61-70.
[22] SNAVELY N. Bundler: structure from motion (SfM) for unordered image collections [EB/OL]. 2008-08-10. http:∥phototour.cs.washington.edu/bundler/.

[1] YANG Xin, XU Duan-qing, ZHAO Lei, YANG Bing. Secondary ray tracing in parallel[J]. J4, 2012, 46(10): 1796-1802.
[2] YANG Xin, WANG Tian-ming, XU Duan-qing. Fast BVH construction on GPU[J]. J4, 2012, 46(1): 84-89.