Real-time stereo visual hull rendering using a multi-GPU-accelerated pipeline

Abstract

Visual hull is an efficient technique for image-based rendering. It takes a group of images as input, produces an approximate geometry model of the object, and renders it from arbitrary new viewpoints. Explicit visual hull models (as polygon meshes or point sets) are usually insufficient in accuracy. Image-based visual hull (IBVH) method [Matusik 2000] reconstructs implicit models, and produce view-dependent rendering results with higher quality.