Gaze correction using 3D video processing for videoconferencing

In this paper, we propose a gaze correction method using 3D video processing techniques including depth estimation and virtual view synthesis. We design a set of color and depth cameras to reduce occlusion regions and improve the depth precision in the less-detailed region. The proposed algorithm deals with fully unsolved problems by fusing the depth data from both depth sensors. Furthermore, view synthesis is performed to create the gaze corrected image from the obtained depth information. Experimental results show our contribution is useful for videoconferencing.