We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3...
Abstract— In this paper, we address the problem of determining the relative position and orientation (pose) of two robots navigating in 2D, based on known egomotion and noisy rob...
We introduce linear methods for model-based tracking of nonrigid 3D objects and for acquiring such models from video. 3D motions and flexions are calculated directly from image in...
This paper introduces a feature based method for the fast generation of sparse 3D point clouds from multiple images with known pose. We extract sub-pixel edge elements (2D positio...