Key points are not available for this paper at this time.
In this paper, we describe an efficient image-based approach to computing and shading visual hulls from silhouette image data. Our algorithm takes advantage of epipolar geometry and incremental computation to achieve a constant rendering cost per rendered pixel. It does not suffer from the computation complexity, limited resolution, or quantization artifacts of previous volumetric approaches. We demonstrate the use of this algorithm in a real-time virtualized reality application running off a small number of video streams. Keywords: Computer Vision, Image-Based Rendering, Constructive Solid Geometry, Misc. Rendering Algorithms. 1 Introduction Visualizing and navigating within virtual environments composed of both real and synthetic objects has been a long-standing goal of computer graphics. The term Virtualized RealityTM, as popularized by Kanade 23, describes a setting where a real-world scene is captured by a collection of cameras and then viewed through a virtual camera, a. . .
Matusik et al. (Sat,) studied this question.