Face image generation method and apparatus, device, and storage medium

A face image generation apparatus, comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• first model generation code configured to cause at least one of the at least one processor to determine, according to a first face image in a first reference element, a three dimensional (3D) morphable model (3DMM) corresponding to the first face image as a first model;
• second model generation code configured to cause at least one of the at least one processor to determine, according to a reference element, a 3DMM corresponding to the reference element as a second model;
• the reference element representing a posture and/or an expression of a target face image;
• determination code configured to cause at least one of the at least one processor to determine, according to the first model and the second model, an initial optical flow map corresponding to the first face image, and deform the first face image according to the initial optical flow map to obtain an initial deformation map corresponding to the first face image;
• acquisition code configured to cause at least one of the at least one processor to obtain, through a convolutional neural network according to the first face image, the initial optical flow map, and the initial deformation map, an optical flow increment map and a visibility probability map that correspond to the first face image;
• and
• target face image generation configured to cause at least one of the at least one processor to generate the target face image according to the first face image and the initial optical flow map, the optical flow increment map, and the visibility probability map.

A non-transitory computer-readable storage medium storing instructions, the instructions being executable by at least one processor to cause at least one of the at least one processor to perform:

• determining, according to a first face image, a three dimensional (3D) morphable model (3DMM) corresponding to the first face image as a first model;
• determining, according to a reference element, a 3DMM corresponding to the reference element as a second model, the reference element representing a posture and/or an expression of a target face image;
• determining, according to the first model and the second model, an initial optical flow map corresponding to the first face image, and deforming the first face image according to the initial optical flow map to obtain an initial deformation map corresponding to the first face image;
• obtaining, through a convolutional neural network according to the first face image, the initial optical flow map, and the initial deformation map, an optical flow increment map and a visibility probability map that correspond to the first face image;
• and
• generating the target face image according to the first face image, the initial optical flow map, the optical flow increment map, and the visibility probability map.