-
公开(公告)号：US12113953B2
公开(公告)日：2024-10-08
申请号：US18077549
申请日：2022-12-08
Abstract: This application provides a three-dimensionalization method and apparatus for a two-dimensional image, an electronic device, and a computer-readable storage medium. The method includes performing depth perception processing on a two-dimensional image, to obtain a depth value of each pixel in the two-dimensional image; performing migration processing on the two-dimensional image from multiple perspectives, to obtain a migration result of the two-dimensional image corresponding to each perspective; determining a color value of each pixel in a migration image corresponding to each perspective, based on the depth value of each pixel in the two-dimensional image and the migration result of the two-dimensional image corresponding to each perspective; generating, based on the color value of each pixel in the migration image of each perspective, the migration image corresponding to the perspective; and encapsulating the migration images of the multiple perspectives in an order, to obtain a three-dimensional video.
-
公开(公告)号：US12045914B2
公开(公告)日：2024-07-23
申请号：US17971279
申请日：2022-10-21
Inventor： Yanze Wu , Yu Li , Xintao Wang , Honglun Zhang , Xun Zhao , Ying Shan
CPC classification number: G06T11/001 , G06T3/02
Abstract: An image coloring method includes: acquiring first color a priori information about an image-to-be-colored; transforming the first color a priori information to obtain second color a priori information aligned with the image-to-be-colored; downsampling the image-to-be-colored to obtain a first image feature; performing modulation coloring processing on the first image feature based on the second color a priori information to obtain a second image feature; and upsampling the second image feature based on the second color a priori information to obtain a first colored image, where the first colored image is aligned with the image-to-be-colored.
-
公开(公告)号：US20230353828A1
公开(公告)日：2023-11-02
申请号：US18199528
申请日：2023-05-19
Inventor： Hanzi Wang , Guangge Wang , Zhongang Qi , Ying Shan
IPC: H04N21/4627 , H04N21/482 , G06V10/774 , G06V10/74 , G06V20/40
CPC classification number: H04N21/4627 , H04N21/4826 , G06V10/774 , G06V10/761 , G06V20/44
Abstract: A model-based data processing method and apparatus that can extract a first training sample set to obtain a second training sample set and a query video, the first training sample set including different types of video samples; process the second training sample set through an embedded layer network in an action recognition model to obtain a first frame feature sequence; process the query video through the embedded layer network to obtain a second frame feature sequence; process the first frame feature sequence through a time sequence relation network in the action recognition model to obtain a first time sequence relation descriptor; process the second frame feature sequence through the time sequence relation network to obtain a second time sequence relation descriptor; and adjust a model parameter of the action recognition model according to the first time sequence relation descriptor and the second time sequence relation descriptor.
-
-
Search Results
3
records
(took 0.013 seconds)
