GPU-Based Optimization of a Free-Viewpoint Video System

Neal Orman, Hansung Kim, Ryuuki Sakamoto, Tomoji Toriyama, Kiyoshi Kogure, Robert Lindeman

Abstract

We present a method for optimizing the
reconstruction and rendering of 3D objects from multiple images
by utilizing the latest features of consumer-level graphics
hardware based on shader model 4.0. We accelerate visual hull
reconstruction by rewriting a shape-from-silhouette algorithm to
execute on the GPU's parallel architecture. Rendering is
optimized through the application of geometry shaders to
generate billboarding microfacets textured with captured images.
We also present a method for handling occlusion in the camera
selection process that is optimized for execution on the GPU.
Execution time is further improved by rendering intermediate
results directly to texture to minimize the number of data
transfers between graphics and main memory. We show our GPU
based system to be significantly more efficient than a purely CPUbased
approach, due to the parallel nature of the GPU, while
maintaining graphical quality.

Keywords

3D Reconstruction; GPGPU; Image-Based Modeling and Rendering; Microfacet Billboarding

Full Text:

PDF(280 KB)
Copyright (c)