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

Leqing Zhu; Xun Wang; Dadong Wang; Huiyan Wang

doi:10.1117/1.OE.55.10.103101

7 October 2016 Single image depth estimation based on convolutional neural network and sparse connected conditional random field

Leqing Zhu, Xun Wang, Dadong Wang, Huiyan Wang

Author Affiliations +

Optical Engineering, Vol. 55, Issue 10, 103101 (October 2016). https://doi.org/10.1117/1.OE.55.10.103101

Abstract

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.

Citation Download Citation

Leqing Zhu, Xun Wang, Dadong Wang, and Huiyan Wang "Single image depth estimation based on convolutional neural network and sparse connected conditional random field," Optical Engineering 55(10), 103101 (7 October 2016). https://doi.org/10.1117/1.OE.55.10.103101

Published: 7 October 2016

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available