A Photometric Image-Based Rendering (PIBR) concept is proposed that facilitates the generation of an image with an arbitrary illumination. Based on this concept, we aim to generat...
Abstract. Recently, on-line adaptation of binary classifiers for tracking have been investigated. On-line learning allows for simple classifiers since only the current view of the ...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
A number of studies have demonstrated that infrared (IR) imagery offers a promising alternative to visible imagery due to it's insensitive to variations in face appearance cau...
Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...