Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...
Abstract. We formulate a robust method using Expectation Maximization (EM) to address the problem of dense photometric stereo. Previous approaches using Markov Random Fields (MRF) ...
We describe an automatic method for building optimal 3D statistical shape models from sets of training shapes. Although shape models show considerable promise as a basis for segmen...
Rhodri H. Davies, Carole J. Twining, Timothy F. Co...
In this paper we propose an extension to the standard Markov Random Field (MRF) model in order to handle layers. Our extension, which we call a Factorial MRF (FMRF), is analogous t...
Abstract. In this paper, we present an approach for image segmentation, based on the existing Active Snake Model and Watershed-based Region Merging. Our algorithm includes initial ...