Title :
Multi-image Matching via Fast Alternating Minimization
Author :
Xiaowei Zhou;Menglong Zhu;Kostas Daniilidis
Author_Institution :
GRASP Lab., Univ. of Pennsylvania, Philadelphia, PA, USA
Abstract :
In this paper we propose a global optimization-based approach to jointly matching a set of images. The estimated correspondences simultaneously maximize pairwise feature affinities and cycle consistency across multiple images. Unlike previous convex methods relying on semidefinite programming, we formulate the problem as a low-rank matrix recovery problem and show that the desired semidefiniteness of a solution can be spontaneously fulfilled. The low-rank formulation enables us to derive a fast alternating minimization algorithm in order to handle practical problems with thousands of features. Both simulation and real experiments demonstrate that the proposed algorithm can achieve a competitive performance with an order of magnitude speedup compared to the state-of-the-art algorithm. In the end, we demonstrate the applicability of the proposed method to match the images of different object instances and as a result the potential to reconstruct category-specific object models from those images.
Keywords :
"Minimization","Optimization","Image matching","Computer vision","Image reconstruction","Computational modeling","Shape"
Conference_Titel :
Computer Vision (ICCV), 2015 IEEE International Conference on
Electronic_ISBN :
2380-7504
DOI :
10.1109/ICCV.2015.459