Fast Image-based Rendering using Hierarchical Image-based Priors

Novel view synthesis using image-based priors has recently been shown to provide high quality renderings of complex 3D scenes. However, current methods are extremely slow, requiring of the order of hours to render a single frame. In this paper we show how a coarse-to-fine method can be used to reduce this time significantly. In contrast to traditional multiple-view stereo methods, devising a coarse-to-fine strategy for this problem is complicated by the fact that image-based priors are strongly tied to the scale at which rendering is performed. We show how a hierarchical decomposition of the texture patch database both allows multiple-scale analysis and speeds up the imposition of the priors. Examples are shown on a number of challenging sequences, and illustrate that the new method yields comparable results to the previous method, with significant gains in speed.