公开(公告)号：US20240257554A1

公开(公告)日：2024-08-01

申请号：US18632696

申请日：2024-04-11

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Chao Xu ,  Junwei Zhu ,  Wenqing Chu ,  Ying Tai ,  Chengjie Wang

IPC: G06V40/16 ,  G06V10/46 ,  G10L25/63

CPC classification number: G06V40/171 ,  G06V10/467 ,  G06V40/172 ,  G10L25/63 ,  G06V2201/07

Abstract: An image generation method, performed by an electronic device includes obtaining an original face image frame, audio driving information, and emotion driving information, performing spatial feature extraction on the original face image frame to obtain an original face spatial feature corresponding to the original face image frame; performing feature interaction processing on the audio driving information and the emotion driving information to obtain a face local pose feature of the to-be-adjusted object issuing the voice content with the target emotion; and performing, based on the original face spatial feature and the face local pose feature, face reconstruction processing on the to-be-adjusted object to generate a target face image frame.

公开(公告)号：US12299963B2

公开(公告)日：2025-05-13

申请号：US18051323

申请日：2022-10-31

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Keke He ,  Junwei Zhu ,  Hui Ni ,  Yun Cao ,  Xu Chen ,  Ying Tai ,  Chengjie Wang ,  Jilin Li ,  Feiyue Huang

IPC: G06V10/00 ,  G06V10/75 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06V40/16

Abstract: An image processing method includes performing additional image feature extraction on a training source face image to obtain a source additional image feature, performing identity feature extraction on the training source face image to obtain a source identity feature, inputting a training template face image into an encoder in a to-be-trained face swapping model to obtain a face attribute feature, inputting the source additional image feature, the source identity feature, and the face attribute feature into a decoder in the face swapping model for decoding to obtain a decoded face image, obtaining a target model loss value based on an additional image difference between the decoded face image and a comparative face image, and adjusting the model parameters of the encoder and the decoder based on the target model loss value to obtain the trained face swapping model.