We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
: In this paper, we propose an image driven shape deformation approach for stylizing a 3D mesh using styles learned from existing 2D illustrations. Our approach models a 2D illustr...
This paper presents work on vision based robotic grasping. The proposed method adopts a learning framework where prototypical grasping points are learnt from several examples and ...
We present a new variational level-set-based segmentation
formulation that uses both shape and intensity prior information
learned from a training set. By applying Bayes’
rule...
In this paper we present an algorithm to automatically produce artistic drawings from stereo image pairs. The input to the algorithm is a natural scene, along with a user-defined...