Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?"

There has been considerable success in automated reconstruction for image sequences where small baseline algorithms can be used to establish matches across a number of images. In contrast in the case of widely separated views, methods have generally been restricted to two or three views. In this paper we investigate the problem of establishing relative viewpoints given a large number of images where no ordering information is provided. A typical application would be where images are obtained from different sources or at different times: both the viewpoint (position, orientation, scale) and lighting conditions may vary significantly over the data set. Such a problem is not fundamentally amenable to exhaustive pair wise and triplet wide baseline matching because this would be prohibitively expensive as the number of views increases. Instead, we investiate how a combination of image invariants, covariants, and multiple view relations can be used in concord to enable efficient multiple vie...

• Type: Conference
• Year: 2002
• Where: ECCV
• Authors: Frederik Schaffalitzky, Andrew Zisserman
• Keywords: Computer Vision, ECCV 2002, Image Based Technique, Image Data Sets, Multiple View Matching, Small Baseline Algorithms, Wide Baseline Matching