Performance Evaluation of Narrow Band Methods for Variational Stereo Reconstruction

Convex relaxation techniques allow computing optimal or near-optimal solutions for a variety of multilabel problems in computer vision. Unfortunately, they are quite demanding in terms of memory and computation time making them unpractical for large-scale problems. In this paper, we systematically evaluate to what extent narrow band methods can be employed in order to improve the performance of variational multilabel optimization methods. We review variational methods, we present a narrow band formulation and demonstrate with a number of quantitative experiments that the narrow band formulation leads to a reduction in memory and computation time by orders of magnitude while preserving almost the same quality of results. In particular, we show that this formulation allows computing stereo depth maps for 6 Mpixels aerial image pairs on a single GPU in around one minute.