公开(公告)号：US20220028143A1

公开(公告)日：2022-01-27

申请号：US17498249

申请日：2021-10-11

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

Inventor： Tianshu HU ,  Zhibin HONG

IPC: G06T13/20 ,  G06T13/40 ,  G06T13/80 ,  G10L15/02 ,  G06N20/00

Abstract: Provided are a video generation method and apparatus, a device and a storage medium, relating to the field of artificial intelligence and, in particular, to the fields of computer vision and deep learning. The method includes changing a character emotion of an original character image according to a character emotion feature of a to-be-generated video to obtain a target character image; and driving the target character image by use of a character driving network and based on a speech segment to obtain the to-be-generated video.

公开(公告)号：US20230022550A1

公开(公告)日：2023-01-26

申请号：US17937979

申请日：2022-10-04

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

Inventor： Hanqi GUO ,  Zhibin HONG ,  Tianshu HU

IPC: G06T11/60 ,  G06T9/00

Abstract: An image processing method includes: obtaining a first latent code by encoding an image to be edited in a Style (S) space of a Generative Adversarial Network (GAN), in which the GAN is a StyleGAN; encoding the text description information, obtaining a text code of a Contrastive Language-Image Pre-training (CLIP) model, and obtaining a second latent code by mapping the text code on the S space; obtaining a target latent code that satisfies distance requirements by performing distance optimization on the first latent code and the second latent code; and generating a target image based on the target latent code.

公开(公告)号：US20230145443A1

公开(公告)日：2023-05-11

申请号：US17959727

申请日：2022-10-04

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

Inventor： Tianshu HU ,  Hanqi GUO ,  Junyu HAN ,  Zhibin HONG

IPC: G06T3/40

CPC classification number: G06T3/4038

Abstract: Provided are a video stitching method and an apparatus, an electronic device, and a storage medium. In the video stitching method, an intermediate frame is inserted between a last image frame of a first video and a first image frame of a second video. L image frames are sequentially selected in order from back to front from the first video and L image frames are sequentially selected in order from front to back from the second video separately, and L is a natural number greater than 1. The first video and the second video are stitched together to form a target video according to the intermediate frame, the L image frames in the first video, and the L image frames in the second video.

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.