A homography-based CDVS pipeline for image matchingwith improved resilience to viewpoint changes

Abstract

Compact Descriptors for Visual Search (CDVS) is MPEG proposed standard that will enable efficient and interoperable design of visual search applications using local descriptors. Such descriptors are invariant to rotation and scaling, but are not very robust towards viewpoint changes. In this paper, we address this problem and propose a modified version of the CDVS pipeline that employs image back-projection to compensate for perspective distortion. The proposed technique is based on the homography derived from the correspondence extracted from pairs of matching keypoints. Extensive results show that it improves the CDVS matching accuracy under viewpoint changes while having low complexity.