METHOD FOR CONVERTING VIDEO IMAGE INTO THREE-DIMENSIONAL VIDEO IMAGE USING DEEP LEARNING TECHNIQUE AND APPARATUS THEREOF

摘要

The present invention is to provide a method of converting a two-dimensional (2D) video image photographed using a general camera into a three-dimensional (3D) video image using a deep learning technique. According to the present invention, in a method for converting a video image into a 3D video image, a learning video image is photographed using at least two cameras. A 3D learning video image modeled in three dimension is generated using the learning video image and an artificial neural network model is trained using the learning video image and the learning 3D video image. A video image to be converted is input to the trained artificial neural network model. A 3D video image is generated from the video image by using the trained artificial neural network model. The 3D video image is output.;COPYRIGHT KIPO 2020