Coarse-to-fine region selection and matching

Abstract
We present a new approach to wide baseline matching. We propose to use a hierarchical decomposition of the image domain and coarse-to-fine selection of regions to match. In contrast to interest point matching methods, which sample salient regions to reduce the cost of comparing all regions in two images, our method eliminates regions systematically to achieve efficiency. One advantage of our approach is that it is not restricted to covariant salient regions, which is too restrictive under large viewpoint and leads to few corresponding regions. Affine invariant matching of regions in the hierarchy is achieved efficiently by a coarse-to-fine search of the affine space. Experiments on two benchmark datasets shows that our method finds more correct correspondence of the image (with fewer false alarms) than other wide baseline methods on large viewpoint change. © 2015 IEEE.

Citation
Yang Y, Zhaojin Lu, Sundaramoorthi G (2015) Coarse-to-fine region selection and matching. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2015.7299140.

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Conference/Event Name
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

DOI
10.1109/CVPR.2015.7299140

Permanent link to this record