Multi-image Matching via Fast Alternating Minimization
Authors:
- Xiaowei ZhouXZXiaowei Zhou
- Menglong ZhuMZMenglong Zhu
- Kostas DaniilidisKDKostas Daniilidis
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4032-4040
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
All Related Versions
This publication has 29 references indexed in Scilit:
- Multi-Graph Matching via Affinity Optimization with Graduated Consistency RegularizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Consistency-Driven Alternating Optimization for Multigraph Matching: A Unified ApproachIEEE Transactions on Image Processing, 2015
- Reconstructing PASCAL VOC2014
- Graduated Consistency-Regularized Optimization for Multi-graph Matching2014
- Joint Optimization for Consistent Multiple Graph Matching2013
- Structured Forests for Fast Edge Detection2013
- DeepFlow: Large Displacement Optical Flow with Deep Matching2013
- Exact and stable recovery of rotations for robust synchronizationInformation and Inference: A Journal of the IMA, 2013
- Reweighted Random Walks for Graph Matching2010
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm MinimizationSIAM Review, 2010