Reconstructing Floorplans from Point Clouds Using GAN
-
Published:2023-02-08
Issue:2
Volume:9
Page:39
-
ISSN:2313-433X
-
Container-title:Journal of Imaging
-
language:en
-
Short-container-title:J. Imaging
Author:
Jin Tianxing12, Zhuang Jiayan2ORCID, Xiao Jiangjian2, Xu Ningyuan3, Qin Shihao12
Affiliation:
1. Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315211, China 2. Ningbo Institute of Industrial Technology, Chinese Academy of Sciences, Ningbo 315201, China 3. College of Materials Science and Opto-Electronic Technology, University of Chinese Academy of Sciences, Beijing 100049, China
Abstract
This paper proposed a method for reconstructing floorplans from indoor point clouds. Unlike existing corner and line primitive detection algorithms, this method uses a generative adversarial network to learn the complex distribution of indoor layout graphics, and repairs incomplete room masks into more regular segmentation areas. Automatic learning of the structure information of layout graphics can reduce the dependence on geometric priors, and replacing complex optimization algorithms with Deep Neural Networks (DNN) can improve the efficiency of data processing. The proposed method can retain more shape information from the original data and improve the accuracy of the overall structure details. On this basis, the method further used an edge optimization algorithm to eliminate pixel-level edge artifacts that neural networks cannot perceive. Finally, combined with the constraint information of the overall layout, the method can generate compact floorplans with rich semantic information. Experimental results indicated that the algorithm has robustness and accuracy in complex 3D indoor datasets; its performance is competitive with those of existing methods.
Funder
Natural Science Foundation of Zhejiang Province Ningbo Medical Science and Technology Plan Project
Subject
Electrical and Electronic Engineering,Computer Graphics and Computer-Aided Design,Computer Vision and Pattern Recognition,Radiology, Nuclear Medicine and imaging
Reference31 articles.
1. Ikehata, S., Hang, Y., and Furukawa, Y. (2015, January 7–13). Structured Indoor Modeling. Proceedings of the IEEE International Conference on Computer Vision, Washington, DC, USA. 2. State-of-the-art in Automatic 3D Reconstruction of Structured Indoor Environments;Pintore;Comput. Graph. Forum,2020 3. Chen, J., Liu, C., Wu, J., and Furukawa, Y. (November, January 27). Floor-sp: Inverse cad for floorplans by sequential room-wise shortest path. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea. 4. Furukawa, Y., Curless, B., Seitz, S., and Szeliski, R. (2009, January 20–25). Manhattan-world stereo. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA. 5. Liu, C., Wu, J., and Furukawa, Y. (2018, January 8–14). Floornet: A unified framework for floorplan reconstruction from 3d scans. Proceedings of the European conference on computer vision (ECCV), Munich, Germany.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|