Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net.

翻译：弱监督点云分割在标注极其有限的情况下，因能大幅降低密集三维点标注的高昂成本而备受关注。本文探索了将弱监督学习中常用的一致性正则化方法应用于点云任务，并引入多种数据特异性增强策略——这一方向此前尚未得到充分研究。我们观察到，将一致性约束直接用于弱监督点云分割存在两大局限：一是基于传统置信度筛选带来的伪标签噪声问题，二是因丢弃不可靠伪标签导致的一致性约束不足。为此，我们提出一种新颖的可靠性自适应一致性网络（RAC-Net），通过联合预测置信度与模型不确定性来评估伪标签的可靠性，并对所有未标注点实施一致性训练。该网络根据不同点对应伪标签的可靠性，为其施加差异化的约束强度。在S3DIS和ScanNet-v2基准数据集上的实验结果表明，我们的模型在弱监督点云分割任务中取得了优越性能。相关代码将在https://github.com/wu-zhonghua/RAC-Net 公开发布。