Multi-view human body image synthesis method and device based on human body posture

Abstract

The invention belongs to the technical field of image synthesis, in particular to a method and a device for synthesizing multi-view human body images based on human body posture. The present inventionaims at solving the problems that the prior art can not effectively synthesize a multi-view image of a human being and keep the characteristics of the human being from obvious change. The invention provides a multi-view human body image synthesis method based on human body posture, which comprises the following steps: the original human body posture is converted according to the original human body posture and the target angle of view based on the posture conversion model; based on the foreground conversion model and according to the original foreground image, the original human body postureand the target visual angle human body posture, the original foreground image is converted into the foreground image; based on the multi-view synthetic model and according to the original image and the target foreground image, the multi-view synthetic image of human body is obtained by synthesizing the original image. The method provided by the invention has the beneficial effects of maintaining the characteristics of a person in a composite image and synthesizing a high-quality composite image.

Description

technical field [0001] The invention belongs to the technical field of image synthesis, and in particular relates to a multi-view human body image synthesis method and device based on human body posture. Background technique [0002] Human multi-view image synthesis has important application value in the understanding of human behavior. Using human multi-view synthetic images can effectively solve cross-view problems in computer vision, such as cross-view behavior recognition, cross-view pedestrian re-identification, etc. question. [0003] The existing multi-view image synthesis is mainly aimed at the multi-view synthesis of rigid objects (such as cars, chairs, etc.). . Although the posture of a person is invariant in the three-dimensional space, when performing multi-view synthesis, the human posture in the three-dimensional space is mapped to the two-dimensional space. Perspective human body image synthesis needs to synthesize a two-dimensional pose image corresponding...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the prior art cannot effectively synthesize multi-view images of people and keep the characteristics of people from changing significantly, the first aspect of the present invention provides a human-based A multi-view human body image synthesis method for gestures, including:

Images