公开(公告)号：US20210374924A1

公开(公告)日：2021-12-02

申请号：US17107196

申请日：2020-11-30

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

Inventor： Shaoxiong YANG ,  Chen ZHAO

IPC: G06T5/50 ,  G06F17/18

Abstract: The present disclosure provides a computer-implemented method for translating an image and a computer-implemented method for training an image translation model. In the computer-implemented method for translating an image, an image translation request carrying an original image is obtained. The original image is processed to generate a pre-translated image, a mask image and a deformation parameter. The original image is deformed based on the deformation parameter to obtain a deformed image. The deformed image, the pre-translated image and the mask image are merged to generate a target translated image.

公开(公告)号：US20200301514A1

公开(公告)日：2020-09-24

申请号：US16791128

申请日：2020-02-14

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

Inventor： Chen ZHAO ,  Shaoxiong YANG ,  Yuan GAO

IPC: G06F3/01 ,  G06N3/04 ,  G06F17/18 ,  G06F17/16 ,  G06T7/70

Abstract: The present disclosure provides a gesture recognition method, a device, an electronic device, and a storage medium. The method includes: sequentially performing a recognition process on each image from a target video using a preset recognition model of palm orientation to determine a probability of containing a palm image in each image and a palm normal vector corresponding to each image; determining a group of target images from the target video based on the probability of containing the palm image in each image; and determining a target gesture corresponding to the target video based on the palm normal vector corresponding to each target image in the group of target images.

公开(公告)号：US20210374920A1

公开(公告)日：2021-12-02

申请号：US17115996

申请日：2020-12-09

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

Inventor： Shaoxiong YANG ,  Chen ZHAO

IPC: G06T5/00 ,  G06T7/149 ,  G06T5/50

Abstract: A method for translating an image, a method for training an image translation model, and related electronic devices are proposed. In the method for translating an image, an image translation request carrying an original image is obtained. A down-sampled image is generated by down sampling the original image. A pre-translated image, a mask image, and deformation parameters are generated based on the down-sampled image. A size of the pre-translated image and a size of the mask image are the same as a size of the original image. A deformed image is obtained by deforming original image based on the deformation parameters. The deformed image, the pre-translated image and the mask image are fused to generate a target translation image.