公开(公告)号：US20230071661A1

公开(公告)日：2023-03-09

申请号：US18054711

申请日：2022-11-11

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

Inventor： Haotian PENG ,  Ruizhi CHEN ,  Chen ZHAO

IPC: G06T11/60 ,  G06F40/186 ,  G06F40/20 ,  G06N20/00

Abstract: The present disclosure provides a method for training an image editing model, a method for editing an image, apparatuses, a device, a storage medium and a computer program. An implementation plan is: acquiring a training sample set; and performing training steps as follows: selecting a description text sample and an image sample from the training sample set; determining a text direction vector based on the selected description text sample and a predetermined text template; inputting the text direction vector into a mapping network of the image editing model to obtain a bias vector; determining an image direction vector based on the selected image sample and the bias vector; calculating a loss value based on the text direction vector and the image direction vector; and determining, in response to the loss value meeting a threshold condition, that training of the image editing model is completed.

公开(公告)号：US20220414959A1

公开(公告)日：2022-12-29

申请号：US17939301

申请日：2022-09-07

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

Inventor： Haotian PENG ,  Chen ZHAO

IPC: G06T11/60 ,  G06V10/774 ,  G06V10/82 ,  G06V10/776

Abstract: A method and apparatus for training a virtual image generating model, a method and apparatus for generating a virtual image, a device, a storage medium, and a computer program product are provided. The method for training a virtual image generating model includes: training a first initial model using a standard image sample set and a random vector sample set as first of sample data, to obtain an image generating model; training a second initial model using a test latent vector sample set and a test image sample set as second sample data, to obtain an image encoding model; training a third initial model using a standard image sample set and a descriptive text sample set as third sample data, to obtain an image editing model; and training a fourth initial model using the third sample data based on the above models, to obtain the virtual image generating model.

公开(公告)号：US20220058848A1

公开(公告)日：2022-02-24

申请号：US17516769

申请日：2021-11-02

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

Inventor： Haotian PENG ,  Ruizhi CHEN

IPC: G06T13/40

Abstract: Provided are a virtual avatar driving method and apparatus, a device, and a storage medium. The virtual avatar driving method includes: determining reference pose data of each of bone nodes when driving a skinned mesh bone model of a virtual avatar to a target patch model with a same topology; synchronously driving the skinned mesh bone model according to the reference pose data of each of the bone nodes; and updating the reference pose data of each of the bone nodes for subsequently driving the skinned mesh bone model.