We address an unsupervised object detection and segmentation problem that goes beyond the conventional assumptions of one-to-one object correspondences or model-test settings betwe...
Minsu Cho (Seoul National University), Young Min S...
This paper presents a method for learning 3D object templates from view labeled object images. The 3D template is defined in a joint appearance and geometry space, and is compose...
In recent years, researchers have proposed to introduce statistical shape knowledge into level set based segmentation methods in order to cope with insufficient low-level informati...
In this paper, a novel shape and texture error concealment technique for segmented object-based video scenes is proposed. This technique is different from existing concealment tec...
We present a new method for the detection and estimation of multiple directional illuminants, using a single image of any object with known geometry and Lambertian reflectance. W...