Towards Real-Time Voxel Coloring

Techniques for constructing three-dimensional scene models from two-dimensional images are often slow and unsuitable for interactive, realtime applications. In this paper we explore three methods of enhancing the performance of the voxel coloring reconstruction method. The first approach uses texture mapping to leverage hardware acceleration. The second approach uses spatial coherence and a coarse-to-fine strategy to focus computation on the filled parts of scene space. Finally, the multi-resolution method is extended over time to enhance performance for dynamic scenes. 1 Introduction Construction of 3D scene information from sets of images has long been an active research topic in computer vision. In recent years several systems have evolved that allow 3D scene construction from video [ Kanade et al., 1997, Moezzi et al., 1997 ] . Reconstruction from video allows realistic 3D movies to be recorded and played back from arbitrary vantage points. For many applications scene reconstructi..