Single image depth estimation based on convolutional neural network and sparse connected conditional random field

Zhu Leqing; Wang Xun; Wang DadongWang Huiyan

首页> 外文期刊>Optical Engineering >Single image depth estimation based on convolutional neural network and sparse connected conditional random field

【24h】

Single image depth estimation based on convolutional neural network and sparse connected conditional random field

机译：Single image depth estimation based on convolutional neural network and sparse connected conditional random field

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Deep convolutional neural networks (DCNNs) have attracted significant interest in the computer vision community in the recent years and have exhibited high performance in resolving many computer vision problems, such as image classification. We address the pixel-level depth prediction from a single image by combining DCNN and sparse connected conditional random field (CRF). Owing to the invariance properties of DCNNs that make them suitable for high-level tasks, their outputs are generally not localized enough for detailed pixel-level regression. A multiscale DCNN and sparse connected CRF are combined to overcome this localization weakness. We have evaluated our framework using the well-known NYU V2 depth dataset, and the results show that the proposed method can improve the depth prediction accuracy both qualitatively and quantitatively, as compared to previous works. This finding shows the potential use of the proposed method in three-dimensional (3-D) modeling or 3-D video production from the given two-dimensional (2-D) images or 2-D videos. (C) 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)

著录项

来源
《Optical Engineering》 |2016年第10期|103101-1-103101-8|共8页
作者
Zhu Leqing; Wang Xun; Wang DadongWang Huiyan;
展开▼
作者单位

Zhejiang Gongshang Univ, Sch Comp Sci & Informat Engn, 18 Xuezheng St, Hangzhou 310018, Zhejiang, Peoples R China;

CSIRO, Quantitat Imaging Res Team, POB 76, Epping, NSW 1710, Australia;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种英语
中图分类计量学;光学仪器;
关键词
three-dimensional video; depth estimation; deep learning; convolutional neural network; conditional random field;

Single image depth estimation based on convolutional neural network and sparse connected conditional random field

摘要

著录项

相关主题

期刊订阅