Expression migration model training method, expression migration method and device

Abstract

The invention discloses a training method of an expression migration model applied to the field of artificial intelligence. The method comprises the steps of obtaining a source domain face image, a target domain face image and a face feature image; obtaining a synthetic face image through a to-be-trained expression migration model; obtaining a first discrimination result and a second discrimination result through the discrimination network model; obtaining a category feature vector through an image classification model; and updating model parameters of the to-be-trained expression migration model according to the category feature vector, the first discrimination result and the second discrimination result until a model convergence condition is met, thereby obtaining the expression migration model. The invention further discloses an expression migration method and device. According to the invention, complex image processing does not need to be carried out on the face image, the trainingdifficulty and the training cost are reduced, and the expression migration model can output a more real face image.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a training method for an expression transfer model, a method and a device for expression transfer. Background technique [0002] In recent years, the processing and analysis of facial expressions has become a research hotspot in the field of computer vision and graphics, and facial expression transfer has also been widely used. Wherein, the facial expression transfer refers to mapping the captured real user's expression to another target image, so as to achieve the purpose of transferring the facial expression to the target image. [0003] In existing schemes, expression transfer can be performed in a 3-dimensional (3D) manner. First, a 3D model of the face head needs to be constructed based on the face image, and then the image is warped and transformed based on the corresponding 3D face model. Fusion and other processing, and finally achieve the purpose of faci...

AI Technical Summary

Problems solved by technology

[0004] However, using 3D modeling to construct a face model requires complex calculations. Therefore, in the actual training process, it also needs to consume a lot of computing resources, resulting in high cost and difficulty in model training.

Images