2D-to-Stereo Panorama Conversion Using GAN and Concentric Mosaics

2D-to-Stereo Panorama Conversion Using GAN and Concentric Mosaics

We describe a learning-based technique to automatically convert a 2-D panorama to its stereoscopic version. In particular, we train a generative adversarial network using perspective stereo pairs as inputs. Given a 2-D panorama, we partition it into overlapping local perspective views. To satisfy th...

Full description

Bibliographic Details
Main Authors: Jie Lu, Yang Yang, Ruiyang Liu, Sing Bing Kang, Jingyi Yu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
2D-to-stereo panorama
GAN
concentric mosaics
depth peeling loss
selector
stereo panorama synthesis
Online Access:https://ieeexplore.ieee.org/document/8643911/

Internet

https://ieeexplore.ieee.org/document/8643911/

Similar Items