We introduce a novel image segmentation algorithm that uses translational symmetry as the primary foreground/background separation cue. We investigate the process of identifying and analyzing image regions that present approximate translational symmetry for the purpose of image foreground/background separation. In conjunction with texture-based inpainting, understanding the different see-through layers allows us to perform powerful image manipulations such as recovering a mesh occluded background (as much as 53% occluded area) to achieve the effect of image and photo de-fencing. Our algorithm consists of three distinct phases¨C (1) automatically finding the skeleton structure of a potential frontal layer (fence) in the form of a deformed lattice, (2) separating foreground/background layers using appearance regularity, and (3) occluded foreground inpainting to reveal a complete, non-occluded image. Each of these three tasks presents its own special computational challenges that are not encountered in previous, general image de-layering or texture inpainting applications.

Text Reference

Yanxi Liu, Tamara Belkina, James H. Hayes and Roberto Lublinerman, "Image De-fencing," Computer Vision and Pattern Recognition (CVPR), June, 2008

BibTeX Reference

@inproceedings{Liu_CVPR_2008,
    author = "Yanxi Liu, Tamara Belkina, James H. Hayes and Roberto Lublinerman",
    title = "Image De-fencing",
    booktitle = "Computer Vision and Pattern Recognition (CVPR)",
    month = "June",
    year = "2008",
}