3D Reconstruction by Gluing Pair-Wise Euclidean Reconstructions, or "How to Achieve a Good Reconstruction from Bad Images"

This paper presents a new technique for estimating a multi- view reconstruction given pair-wise Euclidean reconstructions up to rotations, translations and scales. The partial reconstructions are glued by the following three step procedure: (i) Camera rotations consistent with all reconstructions are estimated linearly, (ii) All the pair-wise reconstructions are modified according to the new rotations and refined by bundle adjustment while keeping the corresponding rotations same. (Hi) The refined rotations are used to estimate both camera translations and 3D points using Second Order Cone Programming by minimizing the Linfin- norm. We introduce a new criterion for evaluating importance of an epipolar geometry in influence on the overall 3D geometry. The estimated importance is used to reweight data in the above algorithm to better handle unequiponderantly captured images. The performance of the proposed method is demonstrated on difficult wide base-line image sets.

[1]  David Nistér,et al.  An efficient solution to the five-point relative pose problem , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Andrew Zisserman,et al.  Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?" , 2002, ECCV.

[3]  Amnon Shashua,et al.  Threading Fundamental Matrices , 1998, ECCV.

[4]  Frederik Schaffalitzky,et al.  A minimal solution for relative pose with unknown focal length , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[6]  Jiri Matas,et al.  Towards Complete Free-Form Reconstruction of Complex 3D Scenes from an Unordered Set of Uncalibrated Images , 2004, ECCV Workshop SMVP.

[7]  Tomás Pajdla,et al.  3D reconstruction by fitting low-rank matrices with missing data , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[8]  Tomás Pajdla,et al.  Oriented Matching Constraints , 2001, BMVC.

[9]  Robert Sedgewick,et al.  Algorithms in C : Part 5 : Graph Algo-rithms , 2002 .

[10]  Ian D. Reid,et al.  Camera calibration and the search for infinity , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[11]  Richard Szeliski,et al.  High-quality Image-based Interactive Exploration of Real-World Environments 1 , 2003 .

[12]  Philip H. S. Torr,et al.  Model Selection for Two View Geometry: A Review , 1999, Shape, Contour and Grouping in Computer Vision.

[13]  Olivier D. Faugeras,et al.  A Stability Analysis of the Fundamental Matrix , 1994, ECCV.

[14]  F. Kahl.  Multiple View Geometry and the -norm , 2005 .

[15]  Fredrik Kahl,et al.  Multiple view geometry and the L/sub /spl infin//-norm , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[16]  Stepán Obdrzálek,et al.  Local affine frames for wide-baseline stereo , 2002, Object recognition supported by user interaction for service robots.

[17]  Martial Hebert,et al.  Iterative projective reconstruction from multiple views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[18]  David A. Forsyth,et al.  Bayesian structure from motion , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[19]  H. Opower.  Multiple view geometry in computer vision , 2002 .

[20]  Takeo Kanade,et al.  Shape and motion from image streams under orthography: a factorization method , 1992, International Journal of Computer Vision.

[21]  Andrew W. Fitzgibbon,et al.  Automatic Camera Recovery for Closed or Open Image Sequences , 1998, ECCV.

[22]  David Nistér,et al.  Untwisting a Projective Reconstruction , 2004, International Journal of Computer Vision.

[23]  Jiri Matas,et al.  Two-view geometry estimation unaffected by a dominant plane , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[24]  David W. Jacobs,et al.  Linear fitting with missing data: applications to structure-from-motion and to characterizing intensity images , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  Cordelia Schmid,et al.  A Comparison of Affine Region Detectors , 2005, International Journal of Computer Vision.

[26]  Peter F. Sturm,et al.  A Factorization Based Algorithm for Multi-Image Projective Structure and Motion , 1996, ECCV.