This paper builds on principles of depicting transparency in hand-made line drawings, and develops a method to generate similar, but computer-generated, line drawings in a two-ste...
Abstract. This paper presents a novel approach to unsupervised texture segmentation that relies on a very general nonparametric statistical model of image neighborhoods. The method...
Over the course of the first few months of life, our brains accomplish a remarkable feat. They are able to interpret complex visual images so that instead of being just disconnec...
We propose a geometric approach to 3-D motion segmentation from point correspondences in three perspective views. We demonstrate that after applying a polynomial embedding to the ...
We develop an object classification method that can learn a novel class from a single training example. In this method, experience with already learned classes is used to facilita...