The lack of fine-grained 3D shape segmentation data is the main obstacle to developing learning-based 3D segmentation techniques. We propose an effective semi-supervised method for learning 3D segmentations from a few labeled 3D shapes and a large amount of unlabeled 3D data. For the unlabeled data, we present a novel \emph{multilevel consistency} loss to enforce consistency of network predictions between perturbed copies of a 3D shape at multiple levels: point-level, part-level, and hierarchical level. For the labeled data, we develop a simple yet effective part substitution scheme to augment the labeled 3D shapes with more structural variations to enhance training. Our method has been extensively validated on the task of 3D object semantic segmentation on PartNet and ShapeNetPart, and indoor scene semantic segmentation on ScanNet. It exhibits superior performance to existing semi-supervised and unsupervised pre-training 3D approaches. Our code and trained models are publicly available at \url{https://github.com/isunchy/semi_supervised_3d_segmentation}.

翻译：缺乏细微的 3D 形状分化数据是开发基于学习的 3D 分化技术的主要障碍。 我们建议了一种有效的半监督的半监督方法, 用于从几个标签的 3D 形状和大量未贴标签的 3D 数据中学习 3D 分化 。 对于未贴标签的数据, 我们提出了一个新型的 emph{ 多级一致性} 损失, 以强制三D 形状在不同级别( 点级、 部分级别 和 等级 ) 之间网络预测的一致性。 对于标签的数据, 我们开发了一个简单而有效的部分替代方案, 以更多的结构变异方式来增强标签的 3D 3D 形状。 我们的方法已经被广泛验证为 PartNet 和 ShapeNetPart 上的 3D 对象分化任务, 以及 Scannet 上的室内区段分化 。 它展示了现有半监督和未经监督的3D 前训练方法的优异性表现。 我们的代码和经过培训的模型可以在 https://github.com/ insunchy/semi_ suepmentalmentation_ 3_suvimentmentation_ 3。