Optimal Multi-frame Correspondence with Assignment Tensors
Establishing correspondence between features of a set of images has been a long-standing issue amongst the computer vision community. We propose a method that solves the multi-frame correspondence problem by imposing a rank constraint on the observed scene, i.e. rigidity is assumed. Since our algorithm is based solely on a geometrical (global) criterion, it does not suffer from issues usually associated to local methods, such as the aperture problem.
We model feature matching by introducing the assignment tensor, which allows simultaneous feature alignment for all images, thus providing a coherent solution to the calibrated multi-frame correspondence problem in a single step of linear complexity. Also, an iterative method is presented that is able to cope with the non-calibrated case. Moreover, our method is able to seamlessly reject a large number of outliers in every image, thus also handling occlusion in an integrated manner.
KeywordsCost Function Linear Complexity Measurement Matrix Correspondence Problem Matching Candidate
Unable to display preview. Download preview PDF.
- 2.Nemhauser, G., Wolsey, L.: Integer and Cobinatorial Optimization. John Wiley & Sons, Chichester (1999)Google Scholar
- 3.Dellaert, F., et al.: Structure From Motion Without Correspondence. In: Proc. CVPR, South Carolina, USA (June 2000)Google Scholar
- 4.Fazel, M., Hindi, H., Boyd, S.: A Rank Minimization Heuristic with Application to Minimum Order System Approximation. In: Proc. ACC (June 2001)Google Scholar
- 5.Ferrari, V., Tuytelaars, T., van Gool, L.: Wide-Baseline Multiple-View Correspondences. In: Proc. ICCV (October 2003)Google Scholar
- 9.Maciel, J., Costeira, J.: A Global Solution to Sparse Correspondence Problems. IEEE Transactions on Pattern Analysis and Machine Intelligence 25(2) (February 2003)Google Scholar
- 10.Martinec, D., Pajdla, T.: 3D Reconstruction by Fitting Low-Rank Matrices with Data. In: Proc. CVPR (June 2005)Google Scholar
- 11.Oliveira, R., Costeira, J., Xavier, J.: Optimal Point Correspondence through the Use of Rank Constraints. In: Proc. CVPR, San Diego, USA (June 2005)Google Scholar
- 12.Roy, S., Cox, I.: A Maximum-Flow Formulation of the N-Camera Stereo Correspondence Problem. In: Proc. ICCV (January 1998)Google Scholar
- 13.Shafique, K., Shah, M.: A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence. In: Proc. ICCV (October 2003)Google Scholar
- 14.Sturm, P., Triggs, B.: A factorization based algorithm for multi-image projective structure and motion. In: Proc. ECCV, April 1996, pp. 709–720 (1996)Google Scholar