Shape Completion Using Deep Boltzmann Machine
Joint Authors
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2017, Issue 2017 (31 Dec. 2017), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2017-07-19
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Abstract EN
Shape completion is an important task in the field of image processing.
An alternative method is to capture the shape information and finish the completion by a generative model, such as Deep Boltzmann Machine.
With its powerful ability to deal with the distribution of the shapes, it is quite easy to acquire the result by sampling from the model.
In this paper, we make use of the hidden activation of the DBM and incorporate it with the convolutional shape features to fit a regression model.
We compare the output of the regression model with the incomplete shape feature in order to set a proper and compact mask for sampling from the DBM.
The experiment shows that our method can obtain realistic results without any prior information about the incomplete object shape.
American Psychological Association (APA)
Wang, Zheng& Wu, Qingbiao. 2017. Shape Completion Using Deep Boltzmann Machine. Computational Intelligence and Neuroscience،Vol. 2017, no. 2017, pp.1-10.
https://search.emarefa.net/detail/BIM-1141017
Modern Language Association (MLA)
Wang, Zheng& Wu, Qingbiao. Shape Completion Using Deep Boltzmann Machine. Computational Intelligence and Neuroscience No. 2017 (2017), pp.1-10.
https://search.emarefa.net/detail/BIM-1141017
American Medical Association (AMA)
Wang, Zheng& Wu, Qingbiao. Shape Completion Using Deep Boltzmann Machine. Computational Intelligence and Neuroscience. 2017. Vol. 2017, no. 2017, pp.1-10.
https://search.emarefa.net/detail/BIM-1141017
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1141017