公开(公告)号：US11100617B2

公开(公告)日：2021-08-24

申请号：US16599590

申请日：2019-10-11

Applicant: Korea Advanced Institute of Science and Technology

Inventor： Jean-Charles Bazin ,  Rae Hyuk Jung ,  Seung Joon Lee

IPC: G06T5/00 ,  G06N3/08 ,  G06N3/04 ,  G06T3/60 ,  G06N3/00

Abstract: Proposed are a deep learning method and apparatus for the automatic upright rectification of VR content. The deep learning method for the automatic upright rectification of VR content according to an embodiment may include inputting a VR image, to a neural network and outputting orientation information of the VR image through a trained neural network.

公开(公告)号：US10977831B2

公开(公告)日：2021-04-13

申请号：US16277214

申请日：2019-02-15

Applicant: KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Jean-Charles Bazin ,  Oleksandr Bogdan ,  Viktor Eckstein ,  Francois Rameau

IPC: G06T7/80 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20

Abstract: Disclosed herein is a camera calibration method based on deep learning including acquiring an image captured by a camera and predicting an intrinsic parameter of the camera by applying, to the acquired image, a neural network module trained to predict the intrinsic parameter.