Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping

Page view(s)
0
Checked on
Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping
Title:
Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping
Journal Title:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords:
Publication Date:
21 January 2025
Citation:
Shi, H., Liu, F., Wu, Z., Xu, Y., & Lin, G. (2025). Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3487–3499. https://doi.org/10.1109/tpami.2025.3532284
Abstract:
Recently, some weakly supervised 3D point cloud segmentation methods have been proposed to develop effective models with minimum annotation efforts. Our previous work, W4DTS, proposes a challenging task that utilizes only 0.001% points in outdoor point cloud datasets to achieve an effective segmentation model. However, under an extremely limited annotation budget, the quality of pseudo labels generated by W4DTS is unsatisfactory, which limits the segmentation performance in such scenarios. To solve this issue, we propose a progressive 4D grouping approach to group the annotated and unannotated points across space and time, which can generate high-quality pseudo labels with very sparse annotated points. Moreover, to further improve our progressive 4D grouping approach, we design a cross-frame contrastive learning and a local consistency learning to improve the quality of our 4D grouping. Experimental results reveal that with only 0.001% annotations, our solution significantly outperforms the previous best approach on SemanticKITTI. We also evaluate our framework on the SemanticPOSS dataset and ScribbleKITTI dataset, and achieve performances close to our fully supervised backbone models.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research (A*STAR) - Manufacturing, Trade, and Connectivity Programmatic Fund
Grant Reference no. : M23L7b0021
Description:
© 2025 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
ISSN:
0162-8828
2160-9292
1939-3539
Files uploaded:

File Size Format Action
weakly-sup-pami.pdf 3.29 MB PDF Open