Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

A Hole-filling Method for DIBR Based on Convolutional Neural Network

Not Accessible

Your library or personal account may give you access

Abstract

There are holes for images generated by Depth-Image-Based Rendering (DIBR) method due to occlusion of foreground. An algorithm to fill holes based on convolutional neural networks is presented. PSNR of the image after filling holes is 32.65dB.

© 2018 The Author(s)

PDF Article
More Like This
Convolutional Neural Network based Nonlinear Classifier for 112-Gbps High Speed Optical Link

Chun-Yen Chuang, Li-Chun Liu, Chia-Chien Wei, Jun-Jie Liu, Lindor Henrickson, Wan-Jou Huang, Chih-Lin Wang, Young-Kai Chen, and Jyehong Chen
W2A.43 Optical Fiber Communication Conference (OFC) 2018

Speckle suppression using the convolutional neural network with an exponential linear unit

Tianjiao Zeng, Zhenbo Ren, and Edmund Y. Lam
CW5B.3 Computational Optical Sensing and Imaging (COSI) 2018

Adaptive OpticWavefront Correction using a Convolutional Neural Network

Andrew P. Norton, Noah Toyonaga, Bruce Macintosh, and Steven Chu
OTh3E.4 Adaptive Optics: Analysis, Methods & Systems (AO) 2018

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.