Method for converting 2D film into 3D film based on full convolutional neural network

Abstract

The invention relates to a method for converting a 2D film into a 3D film based on a full convolutional neural network. The method comprises the following steps: 1) extracting the 2D image of each frame in a photographed film's 2D video; 2) using the full convolutional neural network to extract the characteristics of the 2D image of each frame and calculating the depth value; 3) coloring the 2D image of each frame according to its depth value to generate a corresponding 3D image; and 4) integrating all the 3D images in succession to develop a 3D film. Compared with the prior art, the method can well fit the scenes; the depth estimation quality is high; the calculation speed is rapid; and the method can be efficiently used for the conversion of a 2D film to a 3D film in various scenes.

Description

technical field [0001] The invention relates to a method for converting a movie from 2D to 3D, in particular to a method based on a fully convolutional neural network from 2D to 3D. Background technique [0002] 3D video is an extension of traditional 2D video. By adding image depth information, users can experience video content with a sense of three-dimensionality and presence. Three-dimensional display technology has become a hot technology in the current society and is applied in various scenes of life, which has important practical significance. The lack of 3D content and the high shooting cost are the main factors restricting the current development of 3D video. When shooting an existing 3D movie, two video cameras need to be mounted on a special pan-tilt with adjustable angles, and shoot with a specific angle. This has high requirements for photographers to shoot, and the workload has doubled, requiring a balanced processing of dual materials in the later stage, res...

AI Technical Summary

Problems solved by technology

The lack of 3D content and the high shooting cost are the main factors restricting the development of 3D video

In traditional depth image information input applications, dual parallax images are usually used as input to output depth information estimation results, but such applications are difficult to meet the application requirements of video 2D to 3D

Therefore, it is usually necessary to perform stereoscopic display by inputting monocular disparity images, and the current monocular image depth estimation methods are mostly based on geometric models or other visual cues, using manually marked features, which are not suitable for converting 2D movies to 3D movies. application

Images