Visual correspondence using energy minimization and mutual information

J. Kim, V. Kolmogorov, R. Zabih, in:, IEEE, 2003, pp. 1033–1040.

Download
No fulltext has been uploaded. References only!

Conference Paper | Published
Author
; ;
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.
Publishing Year
Date Published
2003-09-30
Volume
2
Page
1033 - 1040
Conference
ICCV: International Conference on Computer Vision
IST-REx-ID

Cite this

Kim J, Kolmogorov V, Zabih R. Visual correspondence using energy minimization and mutual information. In: Vol 2. IEEE; 2003:1033-1040. doi:10.1109/ICCV.2003.1238463
Kim, J., Kolmogorov, V., & Zabih, R. (2003). Visual correspondence using energy minimization and mutual information (Vol. 2, pp. 1033–1040). Presented at the ICCV: International Conference on Computer Vision, IEEE. https://doi.org/10.1109/ICCV.2003.1238463
Kim, Junhwan, Vladimir Kolmogorov, and Ramin Zabih. “Visual Correspondence Using Energy Minimization and Mutual Information,” 2:1033–40. IEEE, 2003. https://doi.org/10.1109/ICCV.2003.1238463.
J. Kim, V. Kolmogorov, and R. Zabih, “Visual correspondence using energy minimization and mutual information,” presented at the ICCV: International Conference on Computer Vision, 2003, vol. 2, pp. 1033–1040.
Kim J, Kolmogorov V, Zabih R. 2003. Visual correspondence using energy minimization and mutual information. ICCV: International Conference on Computer Vision vol. 2. 1033–1040.
Kim, Junhwan, et al. Visual Correspondence Using Energy Minimization and Mutual Information. Vol. 2, IEEE, 2003, pp. 1033–40, doi:10.1109/ICCV.2003.1238463.

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar