Visual Correspondence Using Energy Minimization and Mutual Information

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 grap...

• Type: Conference
• Year: 2003
• Where: ICCV
• Authors: Junhwan Kim, Vladimir Kolmogorov, Ramin Zabih
• Keywords: Computer Vision, Dense Visual Correspondence, Graph Cuts, ICCV 2003, Mutual Information, Mutual Information Suffers, Visual Correspondence Problems