Abstract. This paper addresses the problem of probabilistically modeling 3D human motion for synthesis and tracking. Given the high dimensional nature of human motion, learning an ...
Surface parameterization is a fundamental tool in geometric modeling and processing. Most existing methods deal with simply connected disks. This work introduces a novel method to ...
Generative model learning is one of the key problems in machine learning and computer vision. Currently the use of generative models is limited due to the difficulty in effective...
ROJECTPROJECT ABSTRACTABSTRACTABSTRACT After achieving real-time photorealistic rendering, the computer graphics community is beginning to turn its attention to non-photorealistic ...
This paper presents a technique, based on pre-computed light transport and separable BRDF approximation, for interactive rendering of non-diffuse objects under all-frequency envir...