- 专利标题: Generating gaze corrected images using bidirectionally trained network
-
申请号: US17242849申请日: 2021-04-28
-
公开(公告)号: US11699217B2公开(公告)日: 2023-07-11
- 发明人: Furkan Isikdogan , Timo Gerasimow , Gilad Michael
- 申请人: Intel Corporation
- 申请人地址: US CA Santa Clara
- 专利权人: Intel Corporation
- 当前专利权人: Intel Corporation
- 当前专利权人地址: US CA Santa Clara
- 代理机构: Hanley, Flight & Zimmerman, LLC
- 主分类号: G06T5/00
- IPC分类号: G06T5/00 ; G06V40/18 ; G06T3/00 ; G06T5/20 ; G06T7/73 ; G06F18/214 ; G06F18/21 ; G06V10/764 ; G06V10/82 ; G06V10/44 ; G06V10/98
摘要:
An example apparatus for adjusting eye gaze in images one or more processors to execute instructions to bidirectionally train a neural network; access a target angle and an input image, the input image including an eye in a first position; generate a vector field with the neural network; and generate a gaze-adjusted image based on the vector field, the gaze-adjusted image including the eye in a second position.
公开/授权文献
信息查询