Selection of reference imaged for image-based scene representations

Abstract

In computer vision, an attention has been devoted to image-based scene representations. They allow to construct an arbitrary view of a rigid 3-D scene using transfer from two real 2-D reference images, rather than by rendering an explicit 3-D model. We focus on selecting the optimal set of reference images from a large set of images representing the scene. The selected set minimizes a weighted sum of the number of reference views and the total fit error. We propose two different algorithms for solving this optimization problem. The experimental results on synthetic and real data indicate the feasibility of the approach for one-parameter camera motion. The possibility is shown to extend one of the algorithms for more general cases.