GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds
This addresses the need for reducing human annotation costs in 3D scene understanding, though it is incremental as it builds on existing unsupervised techniques.
The paper tackles the problem of 3D semantic segmentation from raw point clouds by proposing GrowSP, the first purely unsupervised method that identifies complex semantic classes without human labels or pretrained models, achieving performance superior to unsupervised baselines and approaching fully-supervised PointNet.
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.