Back to articles
Articles
Volume: 31 | Article ID: art00021
Image
Depth from stacked light field images using generative adversarial network
  DOI :  10.2352/ISSN.2470-1173.2019.11.IPAS-270  Published OnlineJanuary 2019
Abstract

The estimated depth map provides valuable information in many computer vision applications such as autonomous driving, semantic segmentation and 3D object reconstruction. Since the light field camera capture both the spatial and angular light ray, we can estimate a depth map throughout that properties of light field image. However, estimating a depth map from the light field image has a limitation in term of short baseline and low resolution issues. Even though many approach have been developed, but they still have a clear flaw in computation cost and depth value accuracy. In this paper, we propose a network-based and epipolar plane image (EPI) light field depth estimation technique. Since the light field image consists of many sub-aperture images in a 2D spatial plane, we can stack the sub-aperture images in different directions to handle occlusion problem. However, usually used many light field subaperture images are not enough to construct huge datasets. To increase the number of sub-aperture images for stacking, we train the network with augmented light field datasets. In order to illustrate the effectiveness of our approach, we perform the extensive experimental evaluation through the synthetic and real light field scene. The experimental result outperforms the other depth estimation techniques.

Subject Areas :
Views 19
Downloads 0
 articleview.views 19
 articleview.downloads 0
  Cite this article 

Ji-Hun Mun, Yo-Sung Ho, "Depth from stacked light field images using generative adversarial networkin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XVII,  2019,  pp 270-1 - 270-8,  https://doi.org/10.2352/ISSN.2470-1173.2019.11.IPAS-270

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2019
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA