Unsupervised co-segmentation through region matching

Co-segmentation is defined as jointly partitioning multiple images depicting the same or similar object, into foreground and background. Our method consists of a multiplescale multiple-image generative model, which jointly estimates the foreground and background appearance distributions from several images, in a non-supervised manner. In contrast to other co-segmentation methods, our approach does not require the images to have similar foregrounds and different backgrounds to function properly. Region matching is applied to exploit inter-image information by establishing correspondences between the common objects that appear in the scene. Moreover, computing many-tomany associations of regions allow further applications, like recognition of object parts across images. We report results on iCoseg, a challenging dataset that presents extreme variability in camera viewpoint, illumination and object deformations and poses. We also show that our method is robust against large intra-class ...

• Type: Journal
• Year: 2012
• Where: CVPR
• Authors: José C. Rubio, Joan Serrat, Antonio M. López, Nikos Paragios
• Keywords: Camera Viewpoint, Computer Vision, Cvpr 2012, Extreme Variability, Segmentation Methods