Background Augmentation Generative Adversarial Networks (BAGANs): Effective Data Generation Based on GAN-Augmented 3D Synthesizing

Background Augmentation Generative Adversarial Networks (BAGANs): Effective Data Generation Based on GAN-Augmented 3D Synthesizing

Augmented Reality (AR) is crucial for immersive Human⁻Computer Interaction (HCI) and the vision of Artificial Intelligence (AI). Labeled data drives object recognition in AR. However, manually annotating data is expensive, labor-intensive, and data distribution asymmetry. Scantily labeled...

Full description

Bibliographic Details
Main Authors: Yan Ma, Kang Liu, Zhibin Guan, Xinkai Xu, Xu Qian, Hong Bao
Format: Article
Language:English
Published: MDPI AG 2018-12-01
Series:Symmetry
Subjects:
object recognition
image data synthesizing
human–computer interaction
data synthesizing for immersive HCI
generative adversarial nets
background augmentation generative adversarial networks (BAGANs)
Online Access:https://www.mdpi.com/2073-8994/10/12/734

Internet

https://www.mdpi.com/2073-8994/10/12/734

Similar Items