Wei, J., Lin, G., Yap, K.-H., Liu, F., & Hung, T.-Y. (2024). Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds. IEEE Transactions on Circuits and Systems for Video Technology, 1–1. https://doi.org/10.1109/tcsvt.2023.3336323
Abstract:
Semantic segmentation on 3D point clouds is an
important task for 3D scene understanding. While dense labeling
on 3D data is expensive and time-consuming, only a few works
address weakly supervised semantic point cloud segmentation
methods to relieve the labeling cost by learning from simpler
and cheaper labels. Meanwhile, there are still huge performance
gaps between existing weakly supervised methods and state-
of-the-art fully supervised methods. In this paper, we propose
Dense Supervision Propagation (DSP) to train a semantic point
cloud segmentation network with only a small portion of points
being labeled. We argue that we can better utilize the limited
supervision information as we densely propagate the supervision
signal from the labeled points to other points within and across
the input samples. Specifically, we propose a cross-sample feature
reallocating module to transfer similar features and therefore
re-route the gradients across two samples with common classes
and an intra-sample feature redistribution module to propagate
supervision signals on unlabeled points across and within point
cloud samples. We conduct extensive experiments on public
datasets S3DIS and ScanNet. Our weakly supervised method with
only 10% and 1% of labels can produce competitive results with
the fully supervised counterpart.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Tech- nology and Research (A*STAR) - MTC Programmatic Funds
Grant Reference no. : M23L7b0021
This research / project is supported by the Ministry of Education - AcRF Tier 2 grant
Grant Reference no. : MOE-T2EP20220-0007
This research / project is supported by the Ministry of Education - AcRF Tier 1 grant
Grant Reference no. : RG14/22
This research / project is supported by the A*STAR - Career Development Award (CDA)
Grant Reference no. : 202D8243