Choosing reference views for image-based representation

Abstract

Recently, much attention has been devoted to image-based scene representations. They allow to construct an arbitrary view of a 3-D scene by the interpolation (transfer) from a sparse set of real 2-D (reference) images, rather than by rendering an explicit 3-D model. While many authors address mainly the purely geometrical aspect of the task, we focus on the problem, how to select the optimal set of reference views. Selection of reference views from a dense set of real primary views is posed as a selection and fitting of parametric models. The selected set must minimize a weighted sum of the number of reference views and the total fit error. We propose two different algorithms solving this optimization problem. The experimental results on synthetic and real data indicate the feasibility of the approach for 1-DOF camera movement. We discuss the possibility to extend one of the algorithms for more general case.

We are indebted to Prof. Roger Hersch from the EPFL Lausanne in Switzerland who gave the initial idea, to the Swiss National Fund grant 83H-036863, grants GACR 102/95/1378, and the EU Copernicus No. 1068/1994. A. Leonardis' work was supported by the Austrian FWF grant S7002MAT and Slovenian grants J2-6187, #95-158.