Korea Advanced Institute of Science and Technology

Jean-Charles Bazin

Seung Joon Lee

Oleksandr Bogdan

Francois Rameau

Rae Hyuk Jung

Viktor Eckstein

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.

Deep learning method and apparatus for automatic upright rectification of virtual reality content

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.

Growing community of inventors

Daejeon, South Korea

Jean-Charles Bazin