We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
We propose an unsupervised method for evaluating image segmentation. Common methods are typically based on evaluating smoothness within segments and contrast between them, and the...
We propose a new approach to deal with the first and second order statistics of a set of images. These statistics take into account the images characteristic deformations and thei...
Guillaume Charpiat, Olivier D. Faugeras, Renaud Ke...
to appear in Proc. IEEE International Conference on Computer Vision (ICCV), 2005 Bayesian methods have been extensively used in various applications. However, there are two intrin...
Yunqiang Chen, Hongcheng Wang, Tong Fang, Jason Ty...
This paper presents a new surface content completion framework that can restore both shape and appearance from scanned, incomplete point set inputs. First, the geometric holes can...