Correspondence-free stereo vision for the case of arbitrarily-positioned cameras

The established approach of stereo vision is first to establish correspondences across the input images and then to determine 3D at the intersection of the corresponding projection rays. However, correspondence establishment is often difficult. Aloimonos and Herve (1990) presented an algorithm that could recover the 3D structure of planar surface without establishing point-to-point correspondences. Yet, the algorithm is restricted to images taken under the parallel-axis stereo geometry. In this paper, we present a correspondence-free stereo vision algorithm that could handle image data taken from arbitrarily positioned cameras. The new algorithm has a closed-form expression, requiring no iterative computation. The algorithm is applicable to both planar scenes and scenes that are pictured from a far distance. Experiment results with real image data are presented to illustrate the performance of the algorithm.