Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/106735
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Learning depth from single monocular images using deep convolutional neural fields
Author: Liu, F.
Shen, C.
Lin, G.
Reid, I.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 38(10):2024-2039
Publisher: IEEE
Issue Date: 2016
ISSN: 0162-8828
2160-9292
Statement of
Responsibility: 
Fayao Liu, Chunhua Shen, Guosheng Lin, and Ian Reid
Abstract: In this article, we tackle the problem of depth estimation from single monocular images. Compared with depth estimation using multiple images such as stereo depth perception, depth from monocular images is much more challenging. Prior work typically focuses on exploiting geometric priors or additional sources of information, most using hand-crafted features. Recently, there is mounting evidence that features from deep convolutional neural networks (CNN) set new records for various vision applications. On the other hand, considering the continuous characteristic of the depth values, depth estimation can be naturally formulated as a continuous conditional random field (CRF) learning problem. Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF. In particular, we propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework. We then further propose an equally effective model based on fully convolutional networks and a novel superpixel pooling method, which is about 10 times faster, to speedup the patch-wise convolutions in the deep model. With this more efficient model, we are able to design deeper networks to pursue better performance. Our proposed method can be used for depth estimation of general scenes with no geometric priors nor any extra information injected. In our case, the integral of the partition function can be calculated in a closed form such that we can exactly solve the log-likelihood maximization. Moreover, solving the inference problem for predicting depths of a test image is highly efficient as closed-form solutions exist. Experiments on both indoor and outdoor scene datasets demonstrate that the proposed method outperforms state-of-the-art depth estimation approaches.
Keywords: Depth estimation; conditional random field (CRF); deep convolutional neural networks (CNN); fully convolutional networks; superpixel pooling
Description: Date of publication 2 Dec. 2015; date of current version 12 Sept. 2016.
Rights: © 2015 IEEE
RMID: 0030056018
DOI: 10.1109/TPAMI.2015.2505283
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_106735.pdfRestricted Access1.88 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.