Indoor Depth Estimation from Single Spherical Images
Thiago L. T. da Silveira, Lorenzo Pezzi Dal'Aqua, Cláudio R. Jung · 2018
In this paper we propose a framework for inferring depth from a single spherical image, which can be coupled to any generic planar image monocular depth estimation algorithm. It consists of first inferring depth from overlapping planar patches extracted from the spherical image, and then using a regularized minimization scheme to stitch the patches back to the sphere. We test three state-of-the-art convolutional neural network (CNN)-based methodologies as baseline methods, and for all of them the proposed approach presented better results than applying the CNN directly to the equirectangular projection and to disjoint sections of the sphere according to the scale-invariant mean squared error (SIMSE) metric.