A face image generation method, device, equipment and storage medium

Abstract

The present application discloses a method for generating a human face image, including: determining the corresponding three-dimensional human face variable model as the first model according to the first human face image in the first reference element; determining the corresponding three-dimensional human face variable model according to the second reference element The three-dimensional face variable model is used as the second model; according to the first model and the second model, the initial optical flow map corresponding to the first face image is determined, and the first face image is deformed according to the initial optical flow map to obtain a deformation map ; According to the first face image and its corresponding initial optical flow map and deformation map, the optical flow incremental map and visible probability map are obtained through the convolutional neural network; according to the first face image and its corresponding initial optical flow map, Optical flow incremental map and visible probability map to generate target face image. On the one hand, this method realizes parametric control, and on the other hand, it preserves the original image detail information based on optical flow, so that the generated image is realistic and natural. The application also discloses the corresponding device, equipment and medium.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular to a face image generation method, device, equipment and storage medium. Background technique [0002] Nowadays, face image generation technology is used in many scenarios. One or more face images are used as input to generate other face images similar to the input posture and facial expression; A side face image is used as the basis, and the face image of the person is generated through the face image generation technology. [0003] The existing face image generation technology directly relies on the generative confrontation network to synthesize face images. The parameter space of the generative confrontation network is relatively large, and the model complexity is relatively high. The actual training effect is not good, and it is prone to overfitting , the synthesized face image is not natural enough, and it only targets a specific face image, so it cannot...

AI Technical Summary

Problems solved by technology

[0003] The existing face image generation technology directly relies on the generative confrontation network to synthesize face images. The parameter space of the generative confrontation network is relatively large, and the model complexity is relatively high. The actual training effect is not good, and it is prone to overfitting , resulting in the synthesized face image is not natural enough, and it only targets a specific face image, unable to achieve personalized face synthesis

Images