4 results about "Face synthesis" patented technology

This application relates to a face image processing method, apparatus, computer device, and storage medium. The method includes acquiring a first face image and a second face image, the first face image and the second face image being images of real faces; generating a first updated face image with non-real face image characteristics based on the first face image; adjusting color distribution of the first updated face image according to color distribution of the second face image to obtain a first adjusted face image; acquiring a target face mask of the first face image, the target face mask being generated by randomly deforming a face region of the first face image; and blending the first adjusted face image and the second face image according to the target face mask to obtain a target face image. Accordingly, a diversity of target face images can be generated.

The specification discloses a face synthesis model training method and device, a storage medium and an electronic device. In the method provided in the specification, a face image is obtained and adjusted, an image of a face region of the adjusted face image is taken as a target image, an image obtained by face synthesis of the target image and the face image before adjustment is taken as a training sample, and a face synthesis model to be trained is input. The face synthesis model to be trained is trained with the minimum difference between an optimized image output by the model and the face image before adjustment as a training target. As can be seen from the above method, the method pre-adjusts and synthesizes a face image to obtain a training sample, and then trains a face synthesis model to be trained with the minimum difference between an image output by the model and the face image before adjustment as a training target. The face synthesis model trained by the method can make the difference between the foreground and the background of a face synthesis image smaller.

The invention provides a geometric perception uncertainty Gaussian splashing method for fast speaking face synthesis. According to the method, high-efficiency and high-fidelity synthesis can be carried out on the speaking face under the condition that a large amount of training data is not needed. Specifically, by designing a geometric perception uncertainty module and learning a geometric perception uncertainty relationship between adjacent Gaussian primitives, the mutual perception ability of the Gaussian primitives is effectively enhanced, and the authenticity of facial movement is improved. Meanwhile, a two-stage learning strategy is introduced, unified motion priori suitable for most identities is learned firstly, then rapid personalized motion adaptation is achieved through a fine tuning stage, the calculation cost is remarkably reduced, and the training efficiency is improved. Experimental results show that compared with the prior art, the method shows more excellent performance while keeping high-fidelity synthesis, can remarkably improve the visual quality, the motion synchronism and the generation efficiency of a speaking face synthesis video, and has wider application potential in actual scenes.

The embodiment of the invention provides a face synthesis method and device, electronic equipment and a storage medium, belongs to the technical field of artificial intelligence, and is suitable for financial science and technology and medical science and technology scenes. The method comprises the following steps: acquiring initial face sample data, and performing facial feature extraction on the initial face sample data to obtain sample face features; performing abnormal image cleaning on the initial face sample data based on the sample face features to obtain target face sample data; performing model training on the original face synthesis model based on the target face sample data and the sample face features to obtain a target face synthesis model; performing image remodeling on the reference face image through the target face synthesis model to obtain a target remodeling feature; performing convolution processing on the target remodeling feature through a target face synthesis model to obtain a target convolution feature; and performing face synthesis on the target convolution features through a target face synthesis model to obtain a target face image. According to the embodiment of the invention, the accuracy of face synthesis can be improved.