Image De-Fencing
Abstract
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 forground/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- (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.
Cite
Text
Liu et al. "Image De-Fencing." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587493Markdown
[Liu et al. "Image De-Fencing." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/liu2008cvpr-image/) doi:10.1109/CVPR.2008.4587493BibTeX
@inproceedings{liu2008cvpr-image,
title = {{Image De-Fencing}},
author = {Liu, Yanxi and Belkina, Tamara and Hays, James and Lublinerman, Roberto},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2008},
doi = {10.1109/CVPR.2008.4587493},
url = {https://mlanthology.org/cvpr/2008/liu2008cvpr-image/}
}