Target image generation method and device, server and storage medium

Abstract

The invention provides a target image generation method, a human body posture transformation method and device, a server and a storage medium, and belongs to the technical field of machine vision. According to the scheme provided by the embodiment of the invention, the method comprises: predicting the first transformation parameter through the first image generation model, and adjusting the firstanalytic image based on the first transformation parameter, so that the attitude of the first analytic image is aligned with that of the generated target analytic image; predicting the second transformation parameter through the second image generation model according to the target analysis image obtained by the first image generation model, and adjusting the combined image to be processed and thefirst analysis image based on the second transformation parameter, so that pixels between the image to be processed and the generated target image are aligned, and better image details are achieved.The parsed images before and after transformation are kept in posture alignment, so that the images before and after transformation can be kept in space alignment, and the generated target image not only guarantees space alignment, but also guarantees clear details.

Description

technical field [0001] The present invention relates to the technical field of machine vision, in particular to a target image generation method, a human body posture transformation method, a device, a server and a storage medium. Background technique [0002] In the field of machine vision, human body pose transfer technology is a very hot topic. In simple terms, human body pose transfer is to convert a person in the picture into a target pose given a picture containing a person and a target pose. Of course, human body pose transfer can not only change the pose of the person in the picture, but also change the pose of the person in the video. For example, given a video of a professional dancer as the target video and a video of an amateur dancer, the movements of the amateur dancer can be made to be the same as those of the professional dancer through human pose transfer. [0003] At present, when performing pose migration on a person in an image, the image containing the...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a method for generating a target image, a method for transforming a human body posture, a device, a server, and a storage medium, which are used to solve the problem that the human body posture changes greatly before and after conversion, and the background of some images is relatively complicated. When the GAN network performs large-scale pose transfer on the characters, there will be problems such as spatial misalignment before and after the transfer, and the texture information of the generated image lacks high-frequency parts, resulting in unclear image details and other problems.

Images