High-accuracy stereo depth maps using structured light

TLDR

Stereo algorithm progress outpaces existing datasets, creating a need for more challenging scenes with accurate ground truth. The paper proposes a method to acquire high‑complexity stereo image pairs with pixel‑accurate correspondence via structured light. The method avoids light‑source calibration and produces registered disparity maps for all camera‑projector pairs. The authors released new stereo datasets that are suitable for algorithm evaluation, available at the Middlebury website.

Abstract

Progress in stereo algorithm performance is quickly outpacing the ability of existing stereo data sets to discriminate among the best-performing algorithms, motivating the need for more challenging scenes with accurate ground truth information. This paper describes a method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light. Unlike traditional range-sensing approaches, our method does not require the calibration of the light sources and yields registered disparity maps between all pairs of cameras and illumination projectors. We present new stereo data sets acquired with our method and demonstrate their suitability for stereo algorithm evaluation. Our results are available at http://www.middlebury.edu/stereo/.