Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is even necessary, demonstrating that existing baselines designed under a fully annotated assumption only degrade slightly even when faced with 1% random point annotations. However, beyond this point, e.g., at 0.1% annotations, segmentation accuracy is unacceptably low. We observe that, as point clouds are samples of the 3D world, the distribution of points in a local neighborhood is relatively homogeneous, exhibiting strong semantic similarity. Motivated by this, we propose a new weak supervision method to implicitly augment highly sparse supervision signals. Extensive experiments demonstrate the proposed Semantic Query Network (SQN) achieves promising performance on seven large-scale open datasets under weak supervision schemes, while requiring only 0.1% randomly annotated points for training, greatly reducing annotation cost and effort. The code is available at https://github.com/QingyongHu/SQN.

翻译：完全标注点云高度耗时且成本高昂。随着包含数十亿点的大规模点云数据集日益普遍，我们质疑全标注是否必要，并证明即使在仅面对1%随机点标注的情况下，基于全标注假设设计的现有基线模型性能也仅略有下降。然而，当标注比例进一步降低（例如0.1%标注）时，分割精度将低至不可接受。我们观察到，由于点云是三维世界的采样，局部邻域内点的分布相对均匀，表现出强语义相似性。受此启发，我们提出一种新的弱监督方法，以隐式增强高度稀疏的监督信号。大量实验表明，所提出的语义查询网络（Semantic Query Network, SQN）在弱监督方案下，在七个大规模开放数据集中取得了有前景的性能，且仅需0.1%随机标注点进行训练，大幅降低了标注成本与工作量。代码开源于 https://github.com/QingyongHu/SQN。