公开(公告)号：US20220383574A1

公开(公告)日：2022-12-01

申请号：US17883037

申请日：2022-08-08

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Zhanwang ZHANG ,  Tianshu HU ,  Zhibin HONG ,  Zhiliang XU

IPC: G06T13/00 ,  G10L15/02 ,  G10L15/04 ,  G06V10/774 ,  G06V40/16 ,  G06T7/11 ,  G06T5/50 ,  G10L15/25

Abstract: A virtual object lip driving method performed by an electronic device includes: obtaining a speech segment and target face image data about a virtual object; and inputting the speech segment and the target face image data into a first target model to perform a first lip driving operation, so as to obtain first lip image data about the virtual object driven by the speech segment. The first target model is trained in accordance with a first model and a second model, the first model is a lip-speech synchronization discriminative model with respect to lip image data, and the second model is a lip-speech synchronization discriminative model with respect to a lip region in the lip image data.

公开(公告)号：US20240331093A1

公开(公告)日：2024-10-03

申请号：US18020891

申请日：2022-06-09

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Zhiliang XU ,  Zhibin HONG

IPC: G06T5/50 ,  G06V10/24

CPC classification number: G06T5/50 ,  G06V10/245 ,  G06T2207/20081 ,  G06T2207/20221

Abstract: A method of training a fusion model, a method of fusing an image, an electronic device, and a storage medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision and deep learning technologies, and may be applied to face image processing, face recognition and other scenarios. A specific implementation solution includes: inputting a training source image and a training template image into a fusion model to obtain a training fusion image; performing an attribute alignment transformation on the training fusion image to obtain a training aligned image, wherein an attribute information of the training aligned image is consistent with an attribute information of the training source image; and training the fusion model using an identity loss function, wherein the identity loss function is generated for the training source image and the training aligned image.

公开(公告)号：US20230143452A1

公开(公告)日：2023-05-11

申请号：US17982832

申请日：2022-11-08

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Zhiliang XU ,  Zhibin HONG

IPC: G06T7/55 ,  G06V10/40 ,  G06V10/24

CPC classification number: G06T7/55 ,  G06V10/40 ,  G06V10/24 ,  G06T2207/20221 ,  G06T2207/20084

Abstract: A method for generating an image includes: obtaining a reference image and an image to be processed; extracting target fusion features from the reference image; determining a plurality of depth feature maps corresponding to the reference image based on the target fusion features; obtaining a target feature map by fusing the plurality of depth feature maps based on the target fusion features; and generating a target image by processing the image to be processed based on the target feature map.