Multi-Image Matching via Fast Alternating Minimization
This work addresses the challenge of efficient multi-image matching for computer vision applications, offering a faster alternative to existing convex methods.
The paper tackles the problem of jointly matching multiple images by proposing a global optimization approach that maximizes pairwise feature affinities and cycle consistency, achieving competitive performance with an order of magnitude speedup compared to state-of-the-art methods.
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.