Aligning images in the wild

• Published in: 2012 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
• Main Authors: Wen-Yan Lin, Linlin Liu, Matsushita, Y., Kok-Lim Low, Siying Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2012
• Subjects: Equations; Frequency modulation; Image color analysis; Imaging; Lighting; Robustness; Vectors
• ISBN: 9781467312264; 1467312266
• ISSN: 1063-6919
• DOI: 10.1109/CVPR.2012.6247651

Aligning image pairs with significant appearance change is a long standing computer vision challenge. Much of this problem stems from the local patch descriptors' instability to appearance variation. In this paper we suggest this instability is due less to descriptor corruption and more the difficulty in utilizing local information to canonically define the orientation (scale and rotation) at which a patch's descriptor should be computed. We address this issue by jointly estimating correspondence and relative patch orientation, within a hierarchical algorithm that utilizes a smoothly varying parameterization of geometric transformations. By collectively estimating the correspondence and orientation of all the features, we can align and orient features that cannot be stably matched with only local information. At the price of smoothing over motion discontinuities (due to independent motion or parallax), this approach can align image pairs that display significant inter-image appearance variations.