We address the application of computer vision to semiimmersive teleconferencing, and present a prototype vision system synthesising a physically plausible video of a speaker to be displayed at a remote conferencing station. The main system components are a hierarchical, efficient large-baseline disparity estimation and a view synthesis module. We illustrate and discuss some results with a realspeaker sequence. We regard the development of such a system in the domain of advanced teleconferencing as the main contribution of this work.