Multi-Image Matching via Fast Alternating Minimization

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.

In ICCV'2015

References in corpus (3)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares
• A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting

Cited by in corpus (6)

• Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views
• Learning Dense Correspondence via 3D-guided Cycle Consistency
• Multi-Image Semantic Matching by Mining Consistent Features
• Proposal Flow: Semantic Correspondences from Object Proposals
• Distributable Consistent Multi-Object Matching
• Consistent Multiple Graph Matching with Multi-layer Random Walks Synchronization