3D Point Cloud Instance Segmentation Considering Global Shape Contour Constraints
-
Published:2023-10-12
Issue:20
Volume:15
Page:4939
-
ISSN:2072-4292
-
Container-title:Remote Sensing
-
language:en
-
Short-container-title:Remote Sensing
Author:
Xv Jiabin1ORCID, Deng Fei1
Affiliation:
1. School of Geodesy and Geomatics, Wuhan University, Wuhan 430072, China
Abstract
Aiming to solve the problem that spatially distributed similar instances cannot be distinguished in 3D point cloud instance segmentation, a 3D point cloud instance segmentation network, considering the global shape contour, was proposed. This research used the global-to-local design idea and added the global shape constraint to solve this problem. A Transformer module (Global Shape Attention, GSA) that can capture the shape contour information of the instance in the scene was designed. This module encoded the shape contour information into the Transformer structure as a Key-Value and extracted the instance fused with the global shape contour features, for instance, segmentation. At the same time, the network directly predicted the instance mask in an end-to-end mode, avoiding heavy post-processing algorithms. Many experiments have been conducted on the S3DIS, ScanNet, and STPL3D datasets, and our experimental results showed that our proposed network can efficiently capture the shape contour information of scene instances and can help to alleviate the problem of the difficulty distinguishing between spatially distributed similar instances in a scene, improving the efficiency and stability of instance segmentation.
Funder
The Special Funds for Creative Research
Subject
General Earth and Planetary Sciences
Reference28 articles.
1. Yi, L., Zhao, W., Wang, H., Sung, M., and Guibas, L.J. (2019, January 15–20). GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. 2. Hou, J., Dai, A., and NieBner, M. (2019, January 15–20). 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. 3. Yang, B., Wang, J., Clark, R., Hu, Q., Wang, S., Markham, A., and Trigoni, N. (2019). Advances in Neural Information Processing Systems, Curran Associates, Inc. 4. Wang, W., Yu, R., Huang, Q., and Neumann, U. (2018, January 18–22). SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. 5. Wang, X., Liu, S., Shen, X., Shen, C., and Jia, J. (2019). Associatively Segmenting Instances and Semantics in Point Clouds. arXiv.
|
|