Estimation of large-amplitude motion and disparity fields: application to intermediate view reconstruction

This paper describes a method for establishing dense correspondence between two images in a video sequence (motion) or in a stereo pair (disparity) in case of large displacements. In order to deal with large-amplitude motion or disparity fields, multi-resolution techniques such as blocks matching and optical flow have been used in the past. Although quite successful, these techniques cannot easily cope with motion/disparity discontinuities as they do not explicitly exploit image structure. Additionally, their computational complexity is high; block matching requires examination of numerous vector candidates while optical flow-based techniques are iterative. In this paper, we propose a new approach that addresses both issues. The approach combines feature matching with Delaunay triangulation, and thus reliable long-range correspondences result while the computational complexity is not high (sparse representation). In the proposed approach, feature points are found first using a simple ...

• Type: Conference
• Year: 2001
• Where: VCIP
• Authors: Moustapha Kardouchi, Janusz Konrad, Carlos Vázquez
• Keywords: Communications, Computational Complexity, Delaunay Triangles, Delaunay Triangulation, VCIP 2001