GENERATIVE ADVERSARIAL NETWORK TRAINING METHOD, IMAGE FACE SWAPPING METHOD AND APPARATUS, AND VIDEO FACE SWAPPING METHOD AND APPARATUS

摘要

Disclosed in the embodiments of the present application are a generative adversarial network training method, an image face swapping method and apparatus, and a video face swapping method and apparatus. The generative adversarial network training method comprises: acquiring an original image and a target image; initializing a generator and a discriminator of a generative adversarial network; inputting the original image and the target image into the generator for training to obtain a face-swapped image, wherein the generator extracts an attribute feature map of a first face from the original image, extracts identity features of a second face from the target image, injects the identity features into the attribute feature map to generate a mixed feature map, and decodes the mixed feature map according to the identity features and the attribute feature map to obtain the face-swapped image after the first face is replaced with the second face; inputting the original image and the face-swapped image into the discriminator for training to obtain a decision value; and adjusting the generator and the discriminator according to the decision value, the face-swapped image, the original image, and the target image.