We address visual correspondence problems without assuming that scene points have similar intensities in different views. This situation is common, usually due to nonLambertian 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.
Visual correspondence using energy minimization and mutual information
Proceedings Ninth IEEE International Conference on Computer Vision ; 1033-1040 vol.2
2003-01-01
957901 byte
Conference paper
Electronic Resource
English
Visual Correspondence Using Energy Minimization and Mutual Information
British Library Conference Proceedings | 2003
|Robust point correspondence by concave minimization
British Library Online Contents | 2002
|CORRESPONDENCE - Aircraft Antenna Coupling Minimization Using Genetic Algorithms and Approximations
Online Contents | 2004
|Direct model based visual tracking and pose estimation using mutual information
British Library Online Contents | 2014
|CORRESPONDENCE - Errata: Autofocusing of ISAR Images Based on Entropy Minimization
Online Contents | 2000
|