This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional ...
We describe a method for learning classes of facial motion patterns from video of a human interacting with a computerized embodied agent. The method also learns correlations betwe...
We present an image-based rendering system to viewpoint-navigate through space and time of complex real-world, dynamic scenes. Our approach accepts unsynchronized, uncalibrated mu...
Christian Lipski, Christian Linz, Kai Berger, Anit...
In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably wi...