This paper presents a novel, real-time disparity algorithm developed for immersive teleconferencing. The algorithm combines the Census transform with a hybrid block-and pixelrecursive matching scheme. Computational effort is minimised by the efficient selection of a small number of candidate vectors, guaranteeing both spatial and temporal consistency of disparities. The latter aspect is crucial for 3-D videoconferencing applications, where novel views of the remote conferees must be synthesised with the correct motion parallax. This application requires video processing at ITU-Rec. 601 resolution. The algorithm generates disparity maps in real time and for both directions (left-to-right and right-to-left) on a Pentium III, 800 MHz processor with good quality.