Extracting meaningful 3D human motion information from video sequences is of interest for applications like intelligent humancomputer interfaces, biometrics, video browsing and ind...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
When creating a cel animation, the animators often use 3D character models to add some effects on the character or to generate intermediate images between the key frames. However,...
This paper presents a framework for speech-driven synthesis of real faces from a corpus of 3D video of a person speaking. Video-rate capture of dynamic 3D face shape and colour ap...
Ioannis A. Ypsilos, Adrian Hilton, Aseel Turkmani,...
Increasingly, models of the world are directly built from images. The paper discusses a number of recent developments that try to push the enveloppe of what image-based modeling c...
Luc J. Van Gool, D. Vandemeulen, Gregor A. Kalbere...