Invention Grant
- Patent Title: Neural network-based key point training apparatus and method
-
Application No.: US17762819Application Date: 2020-12-01
-
Publication No.: US12112571B2Publication Date: 2024-10-08
- Inventor: Gyeongsu Chae , Guembuel Hwang
- Applicant: DEEPBRAIN AI INC.
- Applicant Address: KR Seoul
- Assignee: DEEPBRAIN AI INC.
- Current Assignee: DEEPBRAIN AI INC.
- Current Assignee Address: KR Seoul
- Agency: The PL Law Group, PLLC
- Priority: KR 20200081147 2020.07.01
- International Application: PCT/KR2020/017404 2020.12.01
- International Announcement: WO2022/004970A 2022.01.06
- Date entered country: 2022-03-23
- Main IPC: G06V40/16
- IPC: G06V40/16 ; G06T11/00 ; G06V10/774 ; G06V10/82

Abstract:
A neural network-based key point training apparatus according to an embodiment disclosed includes a key point model trained to extract key points from an input image and an image reconstruction model trained to reconstruct the input image with the key points output by the key point model as the input.
Public/Granted literature
- US20220343679A1 NEURAL NETWORK-BASED KEY POINT TRAINING APPARATUS AND METHOD Public/Granted day:2022-10-27
Information query