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 to apply 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.

翻译：弱监督点云分割在极少量标注条件下具有极高需求，旨在缓解密集标注三维点云的高昂成本。本文探索将弱监督学习中常用的一致性正则化方法拓展至点云场景，结合多种数据特异性增强技术，该方向此前尚未得到充分研究。我们观察到，简单地将一致性约束应用于弱监督点云分割存在两大局限性：基于传统置信度选择的伪标签易受噪声干扰，以及因丢弃不可靠伪标签导致一致性约束不足。为此，我们提出新型可靠性自适应一致性网络（RAC-Net），同时利用预测置信度与模型不确定性评估伪标签的可靠性，对所有未标注点实施一致性训练，并根据对应伪标签的可靠性为不同点施加差异化一致性约束。在S3DIS和ScanNet-v2基准数据集上的实验结果表明，本模型在弱监督点云分割中取得了优越性能。相关代码将公开发布。