Obtaining depth map from 2D non stereo images using deep neural networks

Abstract

Purpose Single image depth prediction allows to extract depth information from a usual 2D image without usage of special sensors such as laser sensors, stereo cameras, etc. The purpose of this paper is to solve the problem of obtaining depth information from 2D image by applying deep neural networks (DNNs). Design/methodology/approach Several experiments and topologies are presented: DNN that uses three inputs—sequence of 2D images from videostream and DNN that uses only one input. However, there is no data set, that contains videostream and corresponding depth maps for every frame. So technique of creating data sets using the Blender software is presented in this work. Findings Despite the problem of an insufficient amount of available data sets, the problem of overfitting was encountered. Although created models work on the data sets, they are still overfitted and cannot predict correct depth map for the random images, that were included into the data sets. Originality/value Existing techniques of depth images creation are tested, using DNN.

Digital Restoration of Cultural Heritage With Data-Driven Computing: A Survey

“…The representation of the 3D coordinate includes depth mapping [118], [119], approximation with numerical approaches [120] to estimate the 3D profile along with the X -Y axis such as Z. It is a process to create a virtual 3D system with the help of techniques presented in the section II with a particular system environment.…”