2D-to-3D video frame conversion

• Main Authors: Didyk, Piotr, Calagari, Kiana Ali Asghar, Matusik, Wojciech, Elgharib, Mohamed Abdelaziz A. Mohamed, Kaspar, Alexandre, Hefeeda, Mohamed M
• Format: Patent
• Language: English
• Published: 07.01.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION

A wide spread adoption of 3D videos and technologies is hindered by the lack of high-quality 3D content. One promising solution to address this problem is to use automated 2D-to-3D conversion. However, current conversion methods, while general, produce low-quality results with artefacts that are not acceptable to many viewers. Creating a database of 3D stereoscopic videos with accurate depth is, however, very difficult. Computer generated content can be used to generate high-quality 3D video reference database for 2D-to- 3D conversion. The method transfers depth information from frames in the 3D reference database to the target frame while respecting object boundaries. It computes depth maps from the depth gradients, and outputs a stereoscopic video.