公开(公告)号：US20230089566A1

公开(公告)日：2023-03-23

申请号：US18070689

申请日：2022-11-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Bin Shao ,  Jun Yue ,  Li Qian ,  Songcen Xu ,  Xueyan Huang ,  Yajiao Liu

IPC: H04N21/80 ,  G06T7/00 ,  G06V10/44 ,  G06V20/70 ,  G06V40/16

Abstract: A video generation method, may be applied to the field of image processing and video generation in the field of artificial intelligence. The method includes: receiving a video generation instruction, and obtaining text information and image information in response to the video generation instruction, where the text information includes one or more keywords, and the image information includes N images; obtaining, based on the one or more keywords, an image feature that is in each of the N images and that corresponds to the one or more keywords; and inputting the one or more keywords and image features of the N images into a target generator network to generate a target video, where the target video includes M images, and the M images are images that are generated based on the image features of the N images and that correspond to the one or more keywords.

公开(公告)号：US12254636B2

公开(公告)日：2025-03-18

申请号：US17853799

申请日：2022-06-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kunyang Sun ,  Hao Chen ,  Chunhua Shen ,  Youliang Yan ,  Bin Shao ,  Songcen Xu

IPC: G06T7/12 ,  G06T3/40

Abstract: An instance segmentation method and apparatus are provided. A to-be-trained segmentation network performs the following processing on each instance group that is in a sample original image and that is of pixels of a marked instance, where each instance group includes at least one marked instance, and the processing includes: predicting at least two different first basic feature maps and a first attention feature map corresponding to each first basic feature map; performing weighted processing on the at least two first basic feature maps and pixel values of respective first attention feature maps corresponding to the at least two first basic feature maps, to obtain a first feature fusion map; and training the to-be-trained segmentation network based on the first feature fusion map and the sample original image. A segmentation model can precisely determine pixels of an instance in an original image.

公开(公告)号：US12225271B2

公开(公告)日：2025-02-11

申请号：US18070689

申请日：2022-11-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Bin Shao ,  Jun Yue ,  Li Qian ,  Songcen Xu ,  Xueyan Huang ,  Yajiao Liu

IPC: H04N21/80 ,  G06T7/00 ,  G06V10/44 ,  G06V20/70 ,  G06V40/16

Abstract: A video generation method may be applied to the field of image processing and video generation in the field of artificial intelligence. The method includes: receiving a video generation instruction, and obtaining text information and image information in response to the video generation instruction, where the text information includes one or more keywords, and the image information includes N images; obtaining, based on the one or more keywords, one or more image features that is in each of the N images and corresponds to the one or more keywords; and inputting the one or more keywords and the one or more image features of the N images into a target generator network to generate a target video, where the target video includes M images, and the M images are generated based on the one or more image features of the N images and correspond to the one or more keywords.