Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications,
especially in scene understanding areas. However, most existing methods operate on fully annotated data while manually preparing ground-truth labels at point-level is very
cumbersome and labor-intensive. To address this issue,
we propose a novel weakly supervised method RWSeg that
only requires labeling one object with one point. With these
sparse weak labels, we introduce a unified framework with
two branches to propagate semantic and instance information respectively to unknown regions using self-attention
and a cross-graph random walk method. Specifically, we
propose a Cross-graph Competing Random Walks (CRW)
algorithm that encourages competition among different instance graphs to resolve ambiguities in closely placed objects, improving instance assignment accuracy. RWSeg generates high-quality instance-level pseudo labels. Experimental results on ScanNet-v2 and S3DIS datasets show
that our approach achieves comparable performance with
fully-supervised methods and outperforms previous weakly supervised methods by a substantial margin.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the ASTAR - RIE2020 Industry Alignment Fund - Industry Collaboration Projects (IAFICP) Funding Initiative
Grant Reference no. : I1901E0052
This research / project is supported by the Agency for Science, Technology and Research - MTC Programmatic Funds
Grant Reference no. : M23L7b0021
This research / project is supported by the Agency for Science, Technology and Research - MTC Young Individual Research Grant
Grant Reference no. : M21K3c0130
This research / project is supported by the Ministry of Education - 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