Generation method of three-dimensional image

Abstract

The invention provides a generation method of a three-dimensional image. The generation method of the three-dimensional image comprise, firstly, obtaining an original two-dimensional image to serve as a first view, extracting a plurality of object regions from the original two-dimensional image, and dividing the plurality of object regions into object regions of interest and object regions of non-interest; secondly, performing overall offset on every object region of non-interest according to depth of field of different object regions of non-interest; thirdly, performing fine offset on the regions of interest; and fourthly, generating a second view according to the offset regions of interest and regions of non-interest. According to the technical scheme of the generation method of the three-dimensional image, a three-dimensional image offset amount calculation mode aiming at different showing occasions are provided, and a good three-dimensional visual immersion effect is achieved through a mode of combining regional offset and the fine offset and one the basis of reducing the calculation; meanwhile, insertion and movement of an object of interest can be performed freely and flexibly according to requirements of users, and a more convenient and fast conversion mode for three-dimensional manufacturing of movies, televisions and animations is provided.

Description

technical field [0001] The invention relates to the field of three-dimensional image generation, in particular to a method for generating three-dimensional animation based on multiple target areas. Background technique [0002] At present, the development of 3D technology has been paid more and more attention by people. The principle of 3D imaging is based on the difference in the angle of view when the left and right eyes look at objects. Two left and right eye images with parallax are obtained, and the brain combines these two images with parallax. The distance difference of objects is obtained during image synthesis, thereby forming stereoscopic vision. However, conventional two-dimensional images enter both eyes with images of exactly the same perspective, so the vision and brain cannot extract the real sense of space and three-dimensional relationship of the objects on the screen, so the sense of integration for the audience is much lower than that of 3D images. , the ...

AI Technical Summary

Problems solved by technology

However, conventional two-dimensional images enter both eyes with images of exactly the same perspective, so the vision and brain cannot extract the real sense of space and three-dimensional relationship of the objects on the screen, so the sense of integration for the audience is much lower than that of 3D images. , the most critical technology based on 3D technology is how to simultaneously obtain images from different perspectives

[0003] There are mainly three ways to make three-dimensional images: one is to use a stereo camera or multiple cameras to shoot from multiple perspectives. The shooting and production process is very complicated, which brings certain constraints to the promotion of 3D technology; the second is to use 3D animation production technology to carry out 3D modeling for the image, construct the depth of field of each part of the image, and then obtain the 3D effect. Modeling all objects in the image requires a large amount of computation and a long production cycle; in addition, it uses computer software technology and image processing technology to convert existing two-dimensional animations or other images into three-dimensional animations or Image, because this technology is based on the original two-dimensional video processing, the implementation cost is the lowest and the most convenient, so it has received the greatest attention at home and abroad. Images with complex scenes cannot obtain better immersive effects

Images