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

2018 Conference on Lasers and Electro-Optics Pacific Rim (CLEO-PR) Pub Date : 2018-07-29 DOI:10.1364/CLEOPR.2018.F1F.5

Yongrui Li, X. Sang, Duo Chen, Peng Wang, Huachun Wang, J. Yuan, Kuiru Wang, B. Yan

引用次数: 0

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.

查看原文本刊更多论文

基于卷积神经网络的DIBR补孔方法

基于深度图像渲染(deep - based image - based Rendering, DIBR)方法生成的图像由于前景遮挡存在孔洞。提出了一种基于卷积神经网络的孔填充算法。补孔后图像的PSNR为32.65dB。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2018 Conference on Lasers and Electro-Optics Pacific Rim (CLEO-PR)

自引率

0.00%

发文量