Image data processing method and apparatus and computer readable storage medium

Abstract

The invention discloses an image data processing method and apparatus and a computer readable storage medium. The method comprises the steps of obtaining a first sample image and a second sample image; wherein the first sample image comprises a sample source object; wherein the second sample image comprises a sample virtual object; obtaining key point position information of the sample source object, and generating a to-be-discriminated image corresponding to the first sample image based on the initial image generation model, the first sample image and the key point position information of thesample source object; wherein the to-be-discriminated image comprises a to-be-discriminated virtual object corresponding to the sample source object; correcting network parameters of the initial image generation model based on the sample source object, the sample virtual object and the to-be-discriminated virtual object; and determining the initial image generation model containing the correctednetwork parameters as an image generation model. The image content of the to-be-discriminated image can be enriched, the matching between the to-be-discriminated image and the first sample image can be improved, and the display effect of the to-be-discriminated image can also be improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to an image data processing method, device, and computer-readable storage medium. Background technique [0002] With the continuous emergence of various types of applications, the functions that the applications can provide to users are also continuously enriched. Among them, there are many applications that convert images of real faces into cartoon face images. However, users have higher and higher requirements on the display effect of the cartoon face images generated by the applications. [0003] In the prior art, it is possible to distort the input real face image and then generate a cartoon face image corresponding to the real face image. However, in the process, the degree of distortion is difficult to control, resulting in the cartoon face image generated by distortion. Poor presentation. [0004] Therefore, in the prior art, if the cartoon face image ...

AI Technical Summary

Problems solved by technology

Among them, there are many applications that convert images of real faces to generate cartoon face images. However, users have higher and higher requirements for the display effect of cartoon face images generated by applications.

[0003] In the prior art, the input real face image can be distorted to generate a cartoon face image corresponding to the real face image. However, in the process, the degree of distortion is difficult to control, resulting in the cartoon face image generated by distortion. Poor presentation

[0004] Therefore, in the prior art, if the cartoon face image is directly distorted, the display effect of the cartoon face image generated by the distortion will be poor.

Images