Optical flow rendering

This paper proposes a new approach to image-based rendering that generates an image viewed from an arbitrary camera position and orientation by render ing optical flows extracted from reference images. To derive valid optical flows, we develop an analysis technique that improves the quality of stereo matching. Without using any special equipments such as range cameras, this technique constructs reliable optical flows from a sequence of matching re sults between reference images. We also derive validity conditions of optic al flows and show that the obtained flows satisfy those conditions. Since e nvironment geometry is inferred from the optical flows, we are able to gene rate more accurate images with this additional geometric information. Our a pproach makes it possible to combine an image rendered from optical flows w ith an image generated by a conventional rendering technique through a simp le Z-buffer algorithm.