Image processing method and device, storage medium, electronic device

Abstract

The invention discloses an image processing method and device, a storage medium and an electronic device. Wherein, the method includes: receiving a conversion request, wherein the conversion request is used to request to convert the image style of the first left-eye view and the first right-eye view into a target style; in response to the conversion request, transforming the first The left-eye view and the first right-eye view are converted into a second left-eye view and a second right-eye view, wherein the image style of the second left-eye view and the second right-eye view is the target style, and the second left-eye view and The disparity between the second right-eye view is the same as the disparity between the first left-eye view and the first right-eye view; returns the second left-eye view converted from the first left-eye view and the first right-eye view and Second right eye view. The invention solves the technical problem of relatively high time cost for image style conversion in the related art.

Description

technical field [0001] The present invention relates to the Internet field, in particular, to an image processing method and device, a storage medium, and an electronic device. Background technique [0002] Style transfer (Style Transfer), or called style transfer, is a very interesting application among many image applications. You can use the method of style transfer to "transfer" the style of one picture to another picture. [0003] In order to achieve the above effect, you can pre-analyze images of a certain style, build a mathematical or statistical model for this style, and then change the image to perform style transfer, such as changing its size so that it can better conform to the established model Although the image effect produced by this method is very good, there are great defects: 1) the preparation time is long, and it takes a long time for developers to build a mathematical or statistical model; 2) the flexibility is poor, A model can only do a certain style...

AI Technical Summary

Problems solved by technology

[0003] In order to achieve the above effects, you can pre-analyze images of a certain style, build a mathematical or statistical model for this style, and then change the image to perform style transfer, such as changing its size so that it can better conform to the established model The input of this method is very good, but there are great defects: 1) the preparation time is long, and it takes a long time for developers to build a mathematical or statistical model; 2) the flexibility is poor, A model can only do a certain style or a certain scene, so style transfer based on this form is very limited in practical applications

[0004] For the above problems, no effective solution has been proposed

Images