An AI-empowered Cloud Solution towards End-to-End 2D-to-3D Image Conversion for Autostereoscopic 3D Display

Abstract

Autostereoscopic displays allow the users to view the 3D content on electronic displays without wearing any glasses. However, the content for glass-free 3D displays needs to be in 3D format such that novel views could be synthesized. Unfortunately, nowadays images/videos are still normally captured in 2D which cannot be directly utilized for glass-free 3D displays. In this paper, we introduce an AI-empowered cloud solution towards end-to-end 2D-to-3D image conversion for autostereoscopic 3D displays, or “CONVAS (3D)” in short. Taking a single 2D image as the input, CONVAS (3D) is able to automatically convert the input 2D image and generate an image suitable for a target autostereoscopic 3D display. It is implemented on a web-based server such that it can allow the users to submit the conversion task and to retrieve the results without geographical constraints.