UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Visual correspondence using energy minimization and mutual information

Kim, J; Kolmogorov, V; Zabih, R; (2003) Visual correspondence using energy minimization and mutual information. In: NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS. (pp. 1033 - 1040). IEEE COMPUTER SOC

Full text not available from this repository.

Abstract

We address visual correspondence problems without assuming that scene points have similar intensities in different views. This situation is common, usually due to non-lambertian scenes or to differences between cameras. We use maximization of mutual information, a powerful technique for registering images that requires no a priori model of the relationship between scene intensities in different views. However, it has proven difficult to use mutual information to compute dense visual correspondence. Comparing fixed-size windows via mutual information suffers from the well-known problems of fixed windows, namely poor performance at discontinuities and in low-texture regions. In this paper, we show how to compute visual correspondence using mutual information without suffering from these problems. Using a simple approximation, mutual information can be incorporated into the standard energy minimization framework used in early vision. The energy can then be efficiently minimized using graph cuts, which preserve discontinuities and handle low-texture regions. The resulting algorithm combines the accurate disparity maps that come from graph cuts with the tolerance for intensity changes that comes from mutual information.

Type:Proceedings paper
Title:Visual correspondence using energy minimization and mutual information
Event:9th IEEE International Conference on Computer Vision
Location:NICE, FRANCE
Dates:2003-10-13 - 2003-10-16
ISBN:0-7695-1950-4
Keywords:ALGORITHMS, IMAGES, FIELDS
UCL classification:UCL > School of BEAMS > Faculty of Engineering Science > Computer Science

Archive Staff Only: edit this record