Multi-view Matching for Unordered Image Sets, or “How Do I Organize My Holiday Snaps?”
There has been considerable success in automated reconstruction for image sequences where small baseline algorithms can be used to establish matches across a number of images. In contrast in the case of widely separated views, methods have generally been restricted to two or three views.
In this paper we investigate the problem of establishing relative viewpoints given a large number of images where no ordering information is provided. A typical application would be where images are obtained from different sources or at different times: both the viewpoint (position, orientation, scale) and lighting conditions may vary significantly over the data set.
Such a problem is not fundamentally amenable to exhaustive pair wise and triplet wide baseline matching because this would be prohibitively expensive as the number of views increases. Instead, we investiate how a combination of image invariants, covariants, and multiple view relations can be used in concord to enable efficient multiple view matching. The result is a matching algorithm which is linear in the number of views.
The methods are illustrated on several real image data sets. The output enables an image based technique for navigating in a 3D scene, moving from one image to whichever image is the next most appropriate.
KeywordsSpan Tree Image Patch Invariant Vector Invariant Space Maximally Stable Extremal Region
Unable to display preview. Download preview PDF.
- 1.S. Avidan and A. Shashua. Threading fundamental matrices. In Proc. ECCV, pages 124–140. Springer-Verlag, 1998.Google Scholar
- 2.A. Baumberg. Reliable feature matching across widely separated views. In Proc. CVPR, pages 774–781, 2000.Google Scholar
- 3.P. Beardsley, P. Torr, and A. Zisserman. 3D model acquisition from extended image sequences. In Proc. ECCV, LNCS 1064/1065, pages 683–695. Springer-Verlag, 1996.Google Scholar
- 4.A. W. Fitzgibbon and A. Zisserman. Automatic camera recovery for closed or open image sequences. In Proc. ECCV, pages 311–326. Springer-Verlag, Jun 1998.Google Scholar
- 5.R. Hartley, L. de Agapito, E. Hayman, and I. Reid. Camera calibration and the search for infinity. In Proc. ICCV, pages 510–517, September 1999.Google Scholar
- 6.R. I. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521623049, 2000.Google Scholar
- 7.R. Koch, M. Pollefeys, B. Heigl, L. Van Gool, and H. Niemann. Calibration of hand-held camera sequences for plenoptic modeling. In Proc. ICCV, pages 585–591, 1999.Google Scholar
- 8.T. Lindeberg and J. Gårding. Shape-adapted smoothing in estimation of 3-d depth cues from affine distortions of local 2-d brightness structure. In Proc. ECCV, pages 389–400, May 1994.Google Scholar
- 9.B. D. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In Proc. of the 7th International Joint Conference on Artificial Intelligence, pages 674–679, 1981.Google Scholar
- 10.J. Matas, J. Burianek, and J. Kittler. Object recognition using the invariant pixel-set signature. In Proc. BMVC., pages 606–615, 2000.Google Scholar
- 11.J. Matas, O. Chum, and T. Urban, M. an Pajdla. Distinguished regions for wide-baseline stereo. Research Report CTU-CMP-2001-33, Center for Machine Perception, K333 FEE Czech Technical University, Prague, Czech Republic, November 2001.Google Scholar
- 12.J Matas, M Urban, and T Pajdla. Unifying view for wide-baseline stereo. In B Likar, editor, Proc. Computer Vision Winter Workshop, pages 214–222, Ljubljana, Sloveni, February 2001. Slovenian Pattern Recorgnition Society.Google Scholar
- 13.K. Mikolajczyk and C. Schmid. Indexing based on scale invariant interest points. In Proc. ICCV, 2001.Google Scholar
- 14.K. Mikolajczyk and C. Schmid. An affine invariant interest point detector. In Proc. ECCV. Springer-Verlag, 2002.Google Scholar
- 16.P. Pritchett and A. Zisserman. Wide baseline stereo matching. In Proc. ICCV, pages 754–760, Jan 1998.Google Scholar
- 17.H. S. Sawhney, S. Hsu, and R. Kumar. Robust video mosaicing through topology inference and local to global alignment. In Proc. ECCV, pages 103–119. Springer-Verlag, 1998.Google Scholar
- 18.F. Schaffalitzky and A. Zisserman. Viewpoint invariant texture matching and wide baseline stereo. In Proc. ICCV, Jul 2001.Google Scholar
- 19.F. Schaffalitzky, A. Zisserman, Hartley, R. I., and P. H. S. Torr. A six point solution for structure and motion. In Proc. ECCV, pages 632–648. Springer-Verlag, Jun 2000.Google Scholar
- 20.C. Schmid and R. Mohr. Local greyvalue invariants for image retrieval. IEEE PAMI, 19(5):530–534, May 1997.Google Scholar
- 21.D. Tell and S. Carlsson. Wide baseline point matching using affine invariants computed from intensity profiles. In Proc. ECCV. Springer-Verlag, Jun 2000.Google Scholar
- 22.W. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon. Bundle adjustment: A modern synthesis. In W. Triggs, A. Zisserman, and R. Szeliski, editors, Vision Algorithms: Theory and Practice, LNCS. Springer Verlag, 2000.Google Scholar
- 23.T. Tuytelaars and L. Van Gool. Content-based image retrieval based on local affinely invariant regions. In Int. Conf. on Visual Information Systems, pages 493–500, 1999.Google Scholar
- 24.T. Tuytelaars and L. Van Gool. Wide baseline stereo matching based on local, affinely invariant regions. In Proc. BMVC., pages 412–425, 2000.Google Scholar