Full-automatic rapid generating and completing method for new view in manufacturing of 3D film

Abstract

The invention discloses a full-automatic rapid generating and completing method for new view in manufacturing of 3D film. The method comprise the steps of performing 3D back projection and surface triangulation for the original view image and the depth image according to the camera parameters of the original view; performing 3D space projection rendering for the gridded image surface structure according to the camera parameters of the new view so as to generate the image of the new view and the depth image; expanding the color and depth of a non-empty area in the new view image and the depth image to fill tan empty area by the flooding filling method until the color and depth of all pixels in the empty area are completely filled. With the adoption of the method, the view image and depth of the 3D new view can be efficiently and rapidly synthesized; in addition, the empty area produced by shielding in the new view can be fully automatically rapidly repaired so as to obtain the realistic new view image synthesizing result.

Description

technical field [0001] The invention relates to a processing method for 3D stereoscopic video, in particular to a method for fully automatic and rapid generation and completion of new views in the production of 3D stereoscopic video in the technical field of image synthesis. Background technique [0002] With the increasing popularity of 3D movies, 3D stereoscopic film and television has gradually become the mainstream media format in the film and television industry. Although stereoscopic cameras on the market can be used to directly shoot and generate 3D stereoscopic video, the cost of 3D real shooting technology is high, the cycle is long and the stereoscopic effect adjustment is difficult. Therefore, today's common 3D movie production scheme is to use the method of converting 2D to 3D in the later stage, which has relatively low cost and stronger controllability of stereoscopic effect. Therefore, how to effectively convert 2D video to 3D stereoscopic video has become a ...

AI Technical Summary

Problems solved by technology

The new view generated by horizontal offset does not conform to the stereoscopic geometric projection relationship of the real world, which will cause visual deception; moreover, the simple color diffusion filling method cannot generate a good complementary effect, which will also cause a certain degree of visual deception

[0004] Therefore, the traditional new view synthesis technology has a low degree of automation, and interactive repair requires a lot of manual operations. It is difficult to meet the industry requirements of 3D film and television production (especially 3D movies) for high quality, high efficiency and low cost.

Images