›› 2011, Vol. 26 ›› Issue (6): 1000-1010.doi: 10.1007/s11390-011-1196-6

Special Issue: Artificial Intelligence and Pattern Recognition

• Computer Graphics and Visualization • Previous Articles     Next Articles

Multiview Visibility Estimation for Image-Based Modeling

Liu-Xin Zhang (张柳新), Member, CCF, Ming-Tao Pei (裴明涛), Member, CCF and Yun-De Jia (贾云得), Senior Member, CCF   

  1. Beijing Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology Beijing 100081, China
  • Received:2010-04-02 Revised:2011-05-11 Online:2011-11-05 Published:2011-11-05
  • About author:Liu-Xin Zhang received the Ph.D. degree in computer science from Beijing Institute of Technology in 2010. His research interests in-clude computer vision, human com-puter interaction and intelligent sys-tems. He is a member of China Com-puter Federation.
    Ming-Tao Pei received the Ph.D. degree in computer science from Beijing Institute of Technology in 2004, and served as an associate professor in the School of Computer Science of Beijing Institute of Tech-nology. He was a visiting scholar at the Center of Image and Vision Sci-ence at UCLA from 2009 to 2011. His main research interest is com-puter vision with emphasis on event recognition and ma-chine learning. He is a member of China Computer Fede-ration.
    Yun-De Jia received the Ph.D. degree in mechatronics from Beijing Institute of Technology in 2000. He is currently a professor of computer science, Beijing Institute of Techno-logy. His research interests include computer vision, media computing, human computer interaction and in-telligent systems.
  • Supported by:

    This work was partially supported by the National Natural Science Foundation of China under Grant No. 90920009 and the National High-Tech Research and Development 863 Program of China under Grant No. 2009AA01Z323.

In this paper, we investigate the problem of determining regions in 3D scene visible to some given viewpoints when obstacles are present in the scene. We assume that the obstacles are composed of some opaque objects with closed surfaces. The problem is formulated in an implicit framework where the obstacles are represented by a level set function. The visible and invisible regions of the given viewpoints are determined through an efficient implicit ray tracing technique. As an extension of our approach, we apply the multiview visibility estimation to an image-based modeling technique. The unknown scene geometry and multiview visibility information are incorporated into a variational energy functional. By minimizing the energy functional, the true scene geometry as well as the accurate visibility information of the multiple views can be recovered from a number of scene images. This makes it feasible to handle the visibility problem of multiple views by our approach when the true scene geometry is unknown.

[1] Greene N, Kass M, Miller G. Hierarchical Z-buffer visibility.In Proc. the 20th Annual Conference on Computer Graphicsand Interactive Techniques, Anaheim, USA, Aug. 2-6, 1993,pp.231-240.

[2] Agarwal P K, Micha S. Ray shooting amidst convex polygonsin 2D. Journal of Algorithms, 1996, 21(3): 508-519.

[3] Agarwal P K, Micha S. Ray shooting amidst convex polyhedraand polyhedral terrains in three dimensions. SIAM Journalon Computing, 1996, 25(1): 100-116.

[4] Franklin S C, David F. Interactive ray tracing with the visibi-lity complex. Computers and Graphics, 1999, 23(5): 703-717.

[5] Steven P, William M, Peter-Pike J S, Peter S, Brian S, CharlesH. Interactive ray tracing. In Proc. ACM Symposium onInteractive 3D Graphics, Atlanta, USA, Apr. 26-28, 1999,pp.119-126.

[6] Lempitsky V, Boykov Y, Ivanov D. Oriented visibility formultiview reconstruction. In Proc. the 9th European Con-ference on Computer Vision, Graz, Austria, May 7-13, 2006,pp.226-238.

[7] Vogiatzis G, Torr P, Cipolla R. Multi-view stereo via volu-metric graph-cuts. In Proc. IEEE Computer Society Con-ference on Computer Vision and Pattern Recognition, San Diego, USA, Jun. 20-25, 2005, pp.391-398.

[8] Tran S, Davis L. 3D surface reconstruction using graph cutswith surface constraints. In Proc. the 9th European Con-ference on Computer Vision, Graz, Austria, May 7-13, 2006,pp.219-231.

[9] Esteban C, Schmitt F. Silhouette and stereo fusion for 3D ob-ject modeling. Computer Vision and Image Understanding,2004, 96(3): 367-392.

[10] Kolev K, Klodt M, Brox T, Cremers D. Continuous globaloptimization in multiview 3D reconstruction. InternationalJournal of Computer Vision, 2009, 84(1): 80-96.

[11] Piegel L, Tiller W. The NURBS Book, Second Edition.Springer-Verlag, 1996.

[12] Rogers D F. An introduction to NURBS. Morgan Kaufman,2000.

[13] Edelsbrunner H. Shape reconstruction with Delaunay com-plex. In Proc. the 3rd Latin American Symposium, Cam-pinas, Brazil, Apr. 20-24, 1998, pp.119-132.

[14] Zhang L X, Yang Y M, Jia Y D. State-based visibility for 3Dreconstruction from multiple views. In Proc. ECCV Work-shop on Multi-Camera and Multi-Modal Sensor Fusion Algo-rithms and Applications, Marseille, France, Oct. 12-18, 2008.

[15] ChinWP, Ntafos S. Shortest watchman routes in simple poly-gons. Discrete and Computational Geometry, 1991, 6(1): 9-31.

[16] Tsai Y H, Cheng L T, Burchard P, Osher S, Sapiro G. Visi-bility and its dynamics in a PDE based implicit framework.Journal of Computational Physics, 2004, 199(1): 260-290.

[17] Faugeras O, Keriven R. Variational principles, surface evolu-tion, PDEs, level set methods, and the stereo problem. IEEETransactions on Image Processing, 1998, 7(3): 336-344.

[18] Jin H, Soatto S, Yezzi A. Multi-view beyond Lambert. InProc. IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition, Madison, USA, Jun. 16-22,2003, pp.171-178.

[19] Gargallo P, Prados E, Sturm P. Minimizing the reprojectionerror in surface reconstruction from images. In Proc. the 11thIEEE International Conference on Computer Vision, Rio deJaneiro, Brazil, Oct. 14-20, 2007, pp.1-8.

[20] Osher S, Sethian J A. Fronts propagating with curvature de-pendent speed: Algorithms based on Hamilton-Jacobi formu-lations. Journal of Computational Physics, 1988, 79(1): 14-49.

[21] Osher S, Fedkiw R. Level Set Methods and Dynamic ImplicitSurfaces. Springer-Verlag, 2002.

[22] Alejandro T, Kang S B, Seitz S. Multi-view multi-exposurestereo. In Proc. the 3rd International Symposium on 3DData Processing, Visualization, and Transmission, ChapelHill, USA, Jun. 14-16, 2006, pp.861-868.

[23] Kutulakos K N, Seitz S M. A theory of shape by space car-ving. International Journal of Computer Vision, 2000, 38(3):199-218.

[24] Laurentini A. The visual hull concept for silhouette-basedimage understanding. IEEE Transactions on Pattern Analy-sis and Machine Intelligence, 1994, 16(2): 150-162.

[25] Li C M, Xu C Y, Gui C F, Fox M D. Level set evolutionwithout re-initialization: A new variational formulation. InProc. IEEE Computer Society Conference on Computer Vi-sion and Pattern Recognition, San Diego, USA, Jun. 20-25,2005, pp.430-436.

[26] Chan T, Vese L. Active contours without edges. IEEE Trans-actions on Image Processing, 2001, 10(2): 266-277.

[27] Seitz S M, Curless B, Diebel J, Scharstein D, Szeliski R. Acomparison and evaluation of multi-view stereo reconstructionalgorithms. In Proc. IEEE Computer Society Conference onComputer Vision and Pattern Recognition, New York, USA,Jun. 17-22, 2006, pp.519-526.

[28] http://vision.middlebury.edu/mview, 2006.
No related articles found!
Full text



[1] Tang Tonggao; Zhao Zhaokeng;. Stack Method in Program Semantics[J]. , 1987, 2(1): 51 -63 .
[2] Feng Yulin;. Hierarchical Protocol Analysis by Temporal Logic[J]. , 1988, 3(1): 56 -69 .
[3] Xue Xing; Sun Zhongxiu; Zhou Jianqiang; Xu Xihao;. A Message-Based Distributed Kernel for a Full Heterogeneous Environment[J]. , 1990, 5(1): 47 -56 .
[4] Jin Zhiquan; Liu Chengfei; Sun Zhongxiu; Zhou Xiaofang; Chen Peipei; Gu Jianming;. Design and Implementation of a Heterogeneous Distributed Database System[J]. , 1990, 5(4): 363 -373 .
[5] Liao Xianzhi; Jin Lan;. A Mechanism Supporting the Client/Server Relationship in the Operating System of Distributed System “THUDS”[J]. , 1991, 6(3): 256 -262 .
[6] Sun Yufang;. The UNIX Localization and Chinese Information Processing System[J]. , 1991, 6(4): 370 -375 .
[7] Fei Xianglin; Liao Lei; Wang Hezhen; Wang Chengzao;. Structured Development Environment Based on the Object-Oriented Concepts[J]. , 1992, 7(3): 193 -201 .
[8] Xu Manwu;. An Implementation of Pure Horn Clause Logic Programming in a Reduction System[J]. , 1993, 8(3): 53 -61 .
[9] Gu Junzhong;. An Object-Oriented Transaction Model[J]. , 1993, 8(4): 3 -20 .
[10] Wang Hui; Liu Dayou; Wang Yafei;. Sequential Back-Propagation[J]. , 1994, 9(3): 252 -260 .

ISSN 1000-9000(Print)

CN 11-2296/TP

Editorial Board
Author Guidelines
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: jcst@ict.ac.cn
  Copyright ©2015 JCST, All Rights Reserved