Approximate N-View Stereo

This paper introduces a new multi-view reconstruction problem called approximate N -view stereo. The goal of this problem is to recover a oneparameter family of volumes that are increasingly tighter supersets of an unknown, arbitrarily-shaped 3D scene. By studying 3D shapes that reproduce the input photographs up to a special image transformation called a shuffle transformation, we prove that (1) these shapes can be organized hierarchically into nested supersets of the scene, and (2) they can be computed using a simple algorithm called Approximate Space Carving that is provably-correct for arbitrary discrete scenes (i.e., for unknown, arbitrarily-shaped Lambertian scenes that are defined by a finite set of voxels and are viewed from N arbitrarily-distributed viewpoints inside or around them). The approach is specifically designed to attack practical reconstruction problems, including (1) recovering shape from images with inaccurate calibration information, and (2) building coarse s...

• Type: Conference
• Year: 2000
• Where: ECCV
• Authors: Kiriakos N. Kutulakos
• Keywords: Arbitrarily-shaped 3D Scene, Computer Vision, ECCV 2000, Multi-view Reconstruction Problem, Reconstruction Problems