Jiaxu Liu jiaxu.liu@durham.ac.uk
PGR Student Doctor of Philosophy
U3DS3 : Unsupervised 3D Semantic Scene Segmentation
Liu, Jiaxu; Yu, Zhengdi; Breckon, Toby P; Shum, Hubert P H
Authors
Zhengdi Yu zhengdi.yu@durham.ac.uk
PGR Student Master of Science
Professor Toby Breckon toby.breckon@durham.ac.uk
Professor
Dr Hubert Shum hubert.shum@durham.ac.uk
Associate Professor
Abstract
Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However , it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is still a lack of investigation into fully un-supervised scene segmentation for point clouds, especially for holistic 3D scenes. This paper presents U3DS 3 , as a step towards completely unsupervised point cloud segmen-tation for any holistic 3D scenes. To achieve this, U3DS 3 leverages a generalized unsupervised segmentation method for both object and background across both indoor and outdoor static 3D point clouds with no requirement for model pre-training, by leveraging only the inherent information of the point cloud to achieve full 3D scene segmentation. The initial step of our proposed approach involves generating superpoints based on the geometric characteristics of each scene. Subsequently, it undergoes a learning process through a spatial clustering-based methodology, followed by iterative training using pseudo-labels generated in accordance with the cluster centroids. Moreover, by leverag-ing the invariance and equivariance of the volumetric representations , we apply the geometric transformation on vox-elized features to provide two sets of descriptors for robust representation learning. Finally, our evaluation provides state-of-the-art results on the ScanNet and SemanticKITTI, and competitive results on the S3DIS, benchmark datasets.
Citation
Liu, J., Yu, Z., Breckon, T. P., & Shum, H. P. H. (2024). U3DS3 : Unsupervised 3D Semantic Scene Segmentation. In 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (3747-3756). https://doi.org/10.1109/WACV57701.2024.00372
Conference Name | 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
---|---|
Conference Location | Waikoloa, Hawaii, USA |
Start Date | Jan 3, 2024 |
End Date | Jan 8, 2024 |
Acceptance Date | Oct 24, 2023 |
Online Publication Date | Apr 9, 2024 |
Publication Date | Apr 9, 2024 |
Deposit Date | Nov 7, 2023 |
Publicly Available Date | Apr 9, 2024 |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 3747-3756 |
Series ISSN | 2472-6737 |
Book Title | 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) |
ISBN | 9798350318937 |
DOI | https://doi.org/10.1109/WACV57701.2024.00372 |
Public URL | https://durham-repository.worktribe.com/output/1900650 |
Files
Author Accepted MAnuscript
(7.5 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
This accepted manuscript is licensed under the Creative Commons Attribution licence.
You might also like
Robust Semi-Supervised Anomaly Detection via Adversarially Learned Continuous Noise Corruption
(2023)
Conference Proceeding
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
(2023)
Conference Proceeding
Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation
(2023)
Conference Proceeding
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search