Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
8-2017
Abstract
The parsing of building facades is a key component to the problem of 3D street scenes reconstruction, which is long desired in computer vision. In this paper, we propose a deep learning based method for segmenting a facade into semantic categories. Man-made structures often present the characteristic of symmetry. Based on this observation, we propose a symmetric regularizer for training the neural network. Our proposed method can make use of both the power of deep neural networks and the structure of man-made architectures. We also propose a method to refine the segmentation results using bounding boxes generated by the Region Proposal Network. We test our method by training a FCN-8s network with the novel loss function. Experimental results show that our method has outperformed previous state-of-the-art methods significantly on both the ECP dataset and the eTRIMS dataset. As far as we know, we are the first to employ end-to-end deepconvolutional neural network on full image scale in the task of building facades parsing.
Keywords
Artificial intelligence, Deep neural networks, Facades, Formal languages, Image segmentation, Neural networks, Semantics, Building facades, Convolutional neural network, Learning approach, Learning-based methods, Man-made structures, Segmentation results, Semantic category, State-of-the-art methods, Deep learning
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems | Numerical Analysis and Scientific Computing
Research Areas
Data Science and Engineering
Publication
Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI 2017: Melbourne, Australia, August 19-25
First Page
2301
Last Page
2307
ISBN
9780999241103
Identifier
10.24963/ijcai.2017/320
Publisher
IJCAI
City or Country
San Francisco, CA
Citation
LIU, Hantang; ZHANG, Jialiang; ZHU, Jianke; and HOI, Steven C. H..
Deepfacade: A deep learning approach to facade parsing. (2017). Proceedings of the 26th International Joint Conference on Artificial Intelligence, IJCAI 2017: Melbourne, Australia, August 19-25. 2301-2307.
Available at: https://ink.library.smu.edu.sg/sis_research/3849
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.24963/ijcai.2017/320
Included in
Artificial Intelligence and Robotics Commons, Databases and Information Systems Commons, Numerical Analysis and Scientific Computing Commons