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 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 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方法,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,我们提出了一个新的多层次一致性损失,以强制在多层次(点级、部分级和等级级)的三D 形状受扰动副本之间进行网络预测的一致性。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,以强化标签的 3D 形状,并增加结构上的变异。关于 PartNet 和 ShapeNetPart 的 3D 对象分化任务,以及 ScanNet 的室内景色分化任务,我们的方法得到了广泛的验证。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。 我们的代码和经过培训的模型在 https://github.com/isny/ semire_ survivivised_3_sementmentmentmentationmentationmentation。