L. Li and N. Zhao, "End-to-End Semi-Supervised 3D Instance Segmentation with PCTeacher," 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024, pp. 5352-5358, doi: 10.1109/ICRA57147.2024.10610145.
Abstract:
3D instance segmentation is a fundamental and critical task for enabling robots to operate effectively in
unstructured 3D environments. In order to address the challenges posed by the high demand for large-scale annotated
data and the limited availability of such data in the context
of 3D instance segmentation, we study semi-supervised 3D instance segmentation problem and propose a novel end-to end framework based on the mean teacher paradigm, named PCTeacher. Our PCTeacher generates both point-level and cluster-level pseudo labels to harness knowledge from unlabeled data. It notably enhances the training stability through end-toend
training and improves pseudo-label quality. Specifically, for point-level pseudo labels, PCTeacher employs a multi-view fusion strategy to achieve higher precision and recall. Regarding cluster-level pseudo labels, it introduces a hybrid grouping strategy to generate more potential proposals and utilizes a point-cluster agreement-based thresholding (PCAT) mechanism
to fully exploit cluster-level pseudo labels. By combining and strengthening both point-level and cluster-level pseudo labels, our PCTeacher achieves state-of-the-art performance on two benchmark datasets across multiple labeled data ratios with a more compact network compared to the existing method.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - MTC Programmatic Fund
Grant Reference no. : M23L7b0021