Image de-fencing

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 fourground/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 meshoccluded 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 e...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Yanxi Liu, Tamara Belkina, James Hays, Roberto Lublinerman
• Keywords: Computer Vision, CVPR 2008, Foreground/background Separation Cue, Image Fourground/background Separation, Image Segmentation Algorithm, Powerful Image Manipulations, Texture Inpainting Applications