Tao An, Duan Yueqi, Wei Yi, Lu Jiwen, Zhou Jie
IEEE Trans Image Process. 2022;31:4952-4965. doi: 10.1109/TIP.2022.3190709. Epub 2022 Jul 22.
Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene. However, such strong supervision suffers from large annotation costs, arousing the need to study efficient annotating. In this paper, we discover that the locations of instances matter for both instance and semantic 3D scene segmentation. By fully taking advantage of locations, we design a weakly-supervised point cloud segmentation method that only requires clicking on one point per instance to indicate its location for annotation. With over-segmentation for pre-processing, we extend these location annotations into segments as seg-level labels. We further design a segment grouping network (SegGroup) to generate point-level pseudo labels under seg-level labels by hierarchically grouping the unlabeled segments into the relevant nearby labeled segments, so that existing point-level supervised segmentation models can directly consume these pseudo labels for training. Experimental results show that our seg-level supervised method (SegGroup) achieves comparable results with the fully annotated point-level supervised methods. Moreover, it outperforms the recent weakly-supervised methods given a fixed annotation budget. Code is available at https://github.com/antao97/SegGroup.
大多数现有的点云实例和语义分割方法严重依赖强监督信号，这需要为场景中的每个点提供点级标签。然而，这种强监督存在标注成本高的问题，从而引发了对高效标注方法的研究需求。在本文中，我们发现实例的位置对实例和语义3D场景分割都很重要。通过充分利用位置信息，我们设计了一种弱监督点云分割方法，该方法只需要为每个实例点击一个点来指示其标注位置。通过进行过分割预处理，我们将这些位置标注扩展为段级标签。我们进一步设计了一个段分组网络（SegGroup），通过将未标注的段分层分组到相关的附近已标注段中，在段级标签下生成点级伪标签，以便现有的点级监督分割模型可以直接使用这些伪标签进行训练。实验结果表明，我们的段级监督方法（SegGroup）与完全标注的点级监督方法取得了相当的结果。此外，在给定固定标注预算的情况下，它优于最近的弱监督方法。代码可在https://github.com/antao97/SegGroup获取。
