View : 59 Download: 0

Deep Monocular Depth Estimation via Integration of Global and Local Predictions

Title
Deep Monocular Depth Estimation via Integration of Global and Local Predictions
Authors
Kim Y.Jung H.Min D.Sohn K.
Ewha Authors
민동보
Issue Date
2018
Journal Title
IEEE Transactions on Image Processing
ISSN
1057-7149JCR Link
Citation
IEEE Transactions on Image Processing vol. 27, no. 8, pp. 4131 - 4144
Keywords
2D-to-3D conversionconvolutional neural networksDepth estimationnon-parametric samplingRGB-D database
Publisher
Institute of Electrical and Electronics Engineers Inc.
Indexed
SCI; SCIE; SCOPUS WOS scopus
Document Type
Article
Abstract
Recent works on machine learning have greatly advanced the accuracy of single image depth estimation. However, the resulting depth images are still over-smoothed and perceptually unsatisfying. This paper casts depth prediction from single image as a parametric learning problem. Specifically, we propose a deep variational model that effectively integrates heterogeneous predictions from two convolutional neural networks (CNNs), named global and local networks. They have contrasting network architecture and are designed to capture the depth information with complementary attributes. These intermediate outputs are then combined in the integration network based on the variational framework. By unrolling the optimization steps of Split Bregman iterations in the integration network, our model can be trained in an end-to-end manner. This enables one to simultaneously learn an efficient parameterization of the CNNs and hyper-parameter in the variational method. Finally, we offer a new data set of 0.22 million RGB-D images captured by Microsoft Kinect v2. Our model generates realistic and discontinuity-preserving depth prediction without involving any low-level segmentation or superpixels. Intensive experiments demonstrate the superiority of the proposed method in a range of RGB-D benchmarks, including both indoor and outdoor scenarios. © 1992-2012 IEEE.
DOI
10.1109/TIP.2018.2836318
Appears in Collections:
엘텍공과대학 > 컴퓨터공학과 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE