Results in WP5 Unupervised Buildings and Roads Detection
Results obtained on the ACDC/MICCAI 2017 training dataset
based on Tree Equipartition, Bayesian Flooding and Region Merging
An exemplar-based framework is used for image completion,
texture synthesis and image inpainting. The tasks are posed in the form of a
discrete global optimization problem. The objective function of this problem is always well-defined and corresponds to the energy of a discrete MRF.
For efficiently optimizing this MRF, a novel optimization scheme,
called Priority-BP, is used.
For more information, you can download the corresponding papers at
CVPR 2006 and
Trans. on Image Processing.
For further information you can download the corresponding publication.
Automatic/semi-automatic 3-D layering
The demonstrations given below illustrate video segmentation of a scene
in foreground and background areas. The foreground could be composed of several
objects, and the background could be further segmented in regions of