Patent · US Active

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

US11100617B2 · kind B2 · utility

1Cited by

0References

3Claims

0Family size

Assignee

KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY · KR

Inventors

Jean-Charles Bazin · Nagold, DE
Rae Hyuk Jung · Daejeon, KR
Seung Joon Lee · Daejeon, KR

Key dates

Filing date	Oct 11, 2019
Grant date	Aug 24, 2021
Priority date	—
Expiry date	Oct 11, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06T2207/20084
WIPO fieldComputer technology
WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.