For interaction with its environment, a robot is required to learn models of objects and to perceive these models in the livestreams from its sensors. In this paper, we propose a ...
We propose a variational algorithm to jointly estimate the shape, albedo, and light configuration of a Lambertian scene from a collection of images taken from different vantage po...
Hailin Jin, Daniel Cremers, Anthony J. Yezzi, Stef...
As camera resolution increases, high-speed non-contact text capture through a digital camera is opening up a new channel for text capture and understanding. Unfortunately, the cap...
Abstract. One of the main prerequisites for location-based services is knowledge of location. We present a simple algorithm for computing the location of a device based on signal s...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...