We study the problem of 3D semantic segmentation from raw point clouds. Unlike existing methods which primarily rely on a large amount of human annotations for training neural networks, we propose the first purely unsupervised method, called GrowSP, to successfully identify complex semantic classes for every point in 3D scenes, without needing any type of human labels or pretrained models. The key to our approach is to discover 3D semantic elements via progressive growing of superpoints. Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation. We extensively evaluate our method on multiple datasets, demonstrating superior performance over all unsupervised baselines and approaching the classic fully-supervised PointNet. We hope our work could inspire more advanced methods for unsupervised 3D semantic learning.

翻译：我们研究从原始点云进行三维语义分割的问题。与现有主要依赖大量人工标注来训练神经网络的方法不同，我们提出了首个纯无监督方法GrowSP，能够在无需任何类型人工标签或预训练模型的情况下，成功识别三维场景中每个点的复杂语义类别。该方法的核心是通过超点的渐进式增长来发现三维语义元素。我们的方法包含三个主要组成部分：1）特征提取器，用于从输入点云中学习逐点特征；2）超点构建器，用于逐步增大超点的尺寸；以及3）语义基元聚类模块，用于将超点汇聚成语义元素，最终实现语义分割。我们在多个数据集上对该方法进行了广泛评估，结果表明其性能优于所有无监督基线方法，并接近经典的全监督PointNet。我们希望这项工作能够启发更先进的无监督三维语义学习方法。