Back to articles
Articles
Volume: 28 | Article ID: art00006
Image
Learning based hole filling method using deep convolutional neural network for view synthesis
  DOI :  10.2352/ISSN.2470-1173.2016.14.IPMVA-376  Published OnlineFebruary 2016
Abstract

In this paper, we propose a novel hole filling method in view synthesis by using deep convolutional neural networks (DCNN). The hole filling networks are learned by end-to-end mapping between hole regions and ground truth images. Hole regions are initially filled with background information. Subsequently hole filling networks restore high quality of hole filling results. The proposed hole filling networks consist of three layers, which are patch and feature extraction layer, non-linear mapping layer, and restoration layer. Experimental results demonstrate that the proposed DCNN-based hole filling method is able to significantly improve hole filling performance, compared to conventional hole filling methods. Furthermore, responses of filters learned by proposed DCNN show that the proposed hole filling framework could provide visually plausible image structures and textures to hole regions.

Subject Areas :
Views 19
Downloads 5
 articleview.views 19
 articleview.downloads 5
  Cite this article 

Heoun-taek Lim, Hak Gu Kim, Yong Man Ro, "Learning based hole filling method using deep convolutional neural network for view synthesisin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Machine Vision Applications IX,  2016,  https://doi.org/10.2352/ISSN.2470-1173.2016.14.IPMVA-376

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA