Structure from motion (SFM) is the problem of reconstructing the geometry of a scene from a stream of images. In this problem, the geometry of the scene must be inferred from imag...
We consider the task of driving a remote control car at high speeds through unstructured outdoor environments. We present an approach in which supervised learning is first used to...
A generative probabilistic model for objects in images is presented. An object consists of a constellation of features. Feature appearance and pose are modeled probabilistically. ...
We propose a probabilistic formulation of 3D segmentation given a series of images from calibrated cameras. Instead of segmenting each image separately in order to build a 3D surfa...
In this paper, we present a method for automatically creating a 3D model of a scene from a set of range images obtained from unknown viewpoints. Existing 3D modeling approaches re...