We present a novel probabilistic approach to fully automated delineation of tree structures in noisy 2D images and 3D image stacks. Unlike earlier methods that rely mostly on local...
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedu...
Abstract. In this paper, we propose a novel technique to address motion estimation and tracking. Such technique represents the motion field using a regular grid of thin-plate spli...
In this paper we describe an efficient approach to add shadows to volumetric scenes. The light emitted by the lightsource is properly attenuated by the intervening volumetric struc...
In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...