Face attribute editing model training method and face attribute editing method

Abstract

The invention discloses a face attribute editing model training method and a face attribute editing method. The training method comprises the following steps: constructing an initial face attribute editing model according to reconstruction parameters of a face training image, wherein a target adversarial loss function and a similarity loss function are preset in the face attribute editing model; and inputting the face training image into the face attribute editing model, and training the face attribute editing model by using the target adversarial loss function and the similarity loss function to obtain a trained face attribute editing model. According to the technical scheme of the invention, common constraint between the target attribute and the non-target attribute is realized when the face attribute editing model edits the target attribute in the face image, the editing invariance of the non-target attribute is maintained while the target attribute is edited, the editing accuracy of the face attribute editing model for the target attribute is improved, and the real naturalness of the current face image after the target attribute is edited is ensured.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of image processing, and in particular to a training of a human face attribute editing model and a method for editing human face attributes. Background technique [0002] Face attribute editing is an important technology in the field of computer vision. It is widely used in content production, film production and entertainment videos, such as changing bald head, changing hairstyle, changing child, changing star face, etc. Face attribute editing is to give an input image containing a face and the target attribute to be edited, and then transform the input image into a target domain face image with the target attribute, and ensure that other original attribute features in the face image remain unchanged . [0003] At present, a Generative Adversarial Networks (GAN) is usually pre-trained to achieve target attribute editing of face images. At this time, facing the difference between ...

AI Technical Summary

Problems solved by technology

[0004] However, due to the global loss function, there will be a corresponding strong constraint relationship between the input image and the output image of the generative adversarial network, so that although the target attributes in the face image output by the trained generative adversarial network can be edited, they are not consistent with the input Compared with images, while editing the target attributes, it may lead to changes in the background area and non-target attribute areas, making the update of the background area and non-target attribute areas in the output image unnatural, which greatly reduces the editing accuracy of face target attributes.

Images