Method for converting 2D video into 3D video

Abstract

The invention relates to a method for converting a 2D video into a 3D video, belongs to the field of mode identification and computer vision, and aims to eliminate an unpredictable error brought in by scene depth estimation and viewpoint synthesis in the prior art and meanwhile greatly improve a calculation speed. The method disclosed by the invention comprises a training stage and a using stage; the training stage sequentially comprises the steps of data input, feature extraction, feature fusion, viewpoint synthesis and parameter updating; and the using stage sequentially comprises the steps of data input, feature extraction, feature fusion and viewpoint synthesis. In the training stage, a 10<6>-level side-by-side 3D stereoscopic video movie film is trained, scene depth estimation and viewpoint synthesis are simultaneously subjected to optimization solution and parameters are determined, so that pixel-level accuracy prediction of an output right-sided view is ensured, and an error brought in by dividing conversion from the 2D video to the 3D video into two task operations; and after training is completed, conversion from the 2D video to the 3D video can be directly carried out, so that conversion efficiency can be greatly improved, and accuracy of a finally output 3D stereoscopic video is ensured.

Description

technical field [0001] The invention belongs to the field of pattern recognition and computer vision, and in particular relates to a method for converting 2D video into 3D video, which is used to directly convert the plane 2D video captured by a common camera into a left-right 3D stereoscopic video that can be viewed in a cinema. Background technique [0002] With the development of virtual reality technology, immersing the audience in 3D experience has become a very important direction in the field of multimedia entertainment. The 3D experience needs the support of panoramic video and 3D effect. If you want to get the 3D viewing experience of the theater for ordinary flat video, you need to convert the 2D flat video into 3D video. There are many formats of 3D video. For 3D stereoscopic video with left and right formats, usually 2D video is converted to 3D video by first estimating the objects in the 2D video image based on various geometric relationships in the 2D video ima...

AI Technical Summary

Problems solved by technology

On the one hand, these solutions consume a lot of computing resources, and the time cost is relatively high; on the other hand, the depth extraction of the scene and the viewpoint synthesis technology are still being further explored, and there will be large calculation errors in the actual use process. Two parts The error is easy to accumulate and affect the final viewing experience

With the advent of the era of big data, more and more high-quality 3D movies, documentaries, animations and other videos have been produced, but the post-2D to 3D production of current flat videos still consumes huge manpower and material resources

Images