Deep360Up: A Deep Learning-Based Approach for Automatic VR Image Upright Adjustment

Spherical VR cameras can capture high-quality immersive VR images with a 360° field of view. However, in practice, when the camera orientation is not straight, the acquired VR image appears tilted when displayed on a VR headset, which diminishes the quality of the VR experience. To overcome this pro...

Full description

Saved in:

Bibliographic Details
Published in:	Proceedings (IEEE Conference on Virtual Reality and 3D User Interfaces. Online) pp. 1 - 8
Main Authors:	Jung, Raehyuk, Lee, Aiden Seung Joon, Ashtari, Amirsaman, Bazin, Jean-Charles
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.03.2019
Subjects:	Cameras Computing methodologies-Computer graphics-Image manipulation-Image processing Deep learning Estimation Headphones Three-dimensional displays Training Upright adjustment VR content
ISSN:	2642-5254
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Spherical VR cameras can capture high-quality immersive VR images with a 360° field of view. However, in practice, when the camera orientation is not straight, the acquired VR image appears tilted when displayed on a VR headset, which diminishes the quality of the VR experience. To overcome this problem, we present a deep learning-based approach that can automatically estimate the orientation of a VR image and return its upright version. In contrast to existing methods, our approach does not require the presence of lines or horizon in the image, and thus can be applied on a wide range of scenes. Extensive experiments and comparisons with state-of-the-art methods have successfully confirmed the validity of our approach.
ISSN:	2642-5254
DOI:	10.1109/VR.2019.8798326