VocMatch: Efficient Multiview Correspondence for Structure from Motion

Feature matching between pairs of images is a main bottleneck of structure-from-motion computation from large, unordered image sets. We propose an efficient way to establish point correspondences between all pairs of images in a dataset, without having to test each individual pair. The principal message of this paper is that, given a sufficiently large visual vocabulary, feature matching can be cast as image indexing, subject to the additional constraints that index words must be rare in the database and unique in each image. We demonstrate that the proposed matching method, in conjunction with a standard inverted file, is 2-3 orders of magnitude faster than conventional pairwise matching. The proposed vocabulary-based matching has been integrated into a standard SfM pipeline, and delivers results similar to those of the conventional method in much less time.

[1]  Reinhard Koch,et al.  Visual Modeling with a Hand-Held Camera , 2004, International Journal of Computer Vision.

[2]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[3]  Andrew Zisserman,et al.  Video Google: Efficient Visual Search of Videos , 2006, Toward Category-Level Object Recognition.

[4]  David Nistér,et al.  Scalable Recognition with a Vocabulary Tree , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[5]  Michael Isard,et al.  Object retrieval with large vocabularies and fast spatial matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Richard Szeliski,et al.  Modeling the World from Internet Photo Collections , 2008, International Journal of Computer Vision.

[7]  Michael Isard,et al.  Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[8]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[9]  David G. Lowe,et al.  Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration , 2009, VISAPP.

[10]  Jiri Matas,et al.  Geometric min-Hashing: Finding a (thick) needle in a haystack , 2009, CVPR.

[11]  Jiri Matas,et al.  Efficient representation of local geometry for large scale object retrieval , 2009, CVPR.

[12]  Richard Szeliski,et al.  Building Rome in a day , 2009, ICCV.

[13]  Michal Havlena,et al.  Randomized structure from motion based on atomic 3D models from camera triplets , 2009, CVPR.

[14]  Michal Havlena,et al.  Efficient Structure from Motion by Graph Optimization , 2010, ECCV.

[15]  Jan-Michael Frahm,et al.  Building Rome on a Cloudless Day , 2010, ECCV.

[16]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[17]  Daniel P. Huttenlocher,et al.  Location Recognition Using Prioritized Feature Matching , 2010, ECCV.

[18]  Tomás Pajdla,et al.  Multi-view reconstruction preserving weakly-supported surfaces , 2011, CVPR 2011.

[19]  Torsten Sattler,et al.  Fast image-based localization using direct 2D-to-3D matching , 2011, 2011 International Conference on Computer Vision.

[20]  Jan-Michael Frahm,et al.  Modeling and Recognition of Landmark Image Collections Using Iconic Scene Graphs , 2008, International Journal of Computer Vision.

[21]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[22]  Jiri Matas,et al.  Learning Vocabularies over a Fine Quantization , 2013, International Journal of Computer Vision.

[23]  Konrad Schindler,et al.  Optimal Reduction of Large Image Databases for Location Recognition , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[24]  David Martin,et al.  Street View Motion-from-Structure-from-Motion , 2013, 2013 IEEE International Conference on Computer Vision.