This dissertation describes a real-time virtual camera application based on view morphing. This system takes video input from multiple cameras aimed at the same subject from different viewing angles. After performing real-time pattern matching, the system generates synthetic views for a virtual camera that can pan between the real views.

The approach of this dissertation differs from the more common “depth from stereo” approach for generating virtual views in that it does not attempt to reconstruct the 3D structure of the original scene. Instead it takes two 2D images and directly generates the 2D output image by performing only planar operations. At the heart of the system are algorithms and data structures that support the fast inter-image correlation needed for the real-time view morphing.

The contribution of this dissertation is that it demonstrates, through the use of innovative algorithms and data structures, that view morphing can be used as the basis of a real-time video avatar system running on commodity PC hardware.