Processing and analysis of 3D Point clouds are challenging since the 3D spatial coordinates of points are irregular so that 3D points cannot be properly ordered to be fed into deep neural networks (DNNs). To deal with the order problem, a certain transformation is needed in the deep learning pipeline. Transformation of a point cloud into another form often leads to information loss. Several DNNs have been designed for point cloud classification and segmentation in recent years. They address the point order problem and reach impressive performance in tasks such as classification, segmentation, registration, object detection, etc. However, DNNs rely on expensive labeled data. Furthermore, due to the end-to-end optimization, deep features are learned iteratively via backpropagation. To save both labeling and computational costs, it is desired to obtain features in an unsupervised and feedforward one-pass manner.

Unsupervised or self-supervised feature learning for 3D point clouds was investigated. Although no labels are needed, the learned features are not as powerful as the supervised one with degraded performance. Recently, two light-weight point cloud classification methods, PointHop [1] and PointHop++ [2], were proposed. Both of them have an unsupervised feature learning module, and their performance is comparable with state-of-the-art deep learning methods.

By generalizing the PointHop, we propose a new solution for joint point cloud classification and part segmentation here. Our main contribution is the development of an unsupervised feedforward feature (UFF) learning system [3] with an encoder-decoder architecture. UFF exploits the statistical correlation between points in a point cloud set to learn shape and point features in a one-pass feedforward manner. It obtains the global shape features with an encoder and the local point features using the encoder-decoder cascade. The shape/point features are then fed into classifiers for shape classification and point classification (i.e. part segmentation). Experiments are conducted to evaluate the performance of the UFF method. For shape classification, UFF is superior to all previous unsupervised methods and on par with state-of-the-art DNNs. For part segmentation, UFF outperforms semi-supervised methods and performs slightly worse than DNNs

[1] M. Zhang, H. You, P. Kadam, S. Liu, and C.-C. J. Kuo, “Pointhop: An explainable machine learning method for point cloud classification,” IEEE Transactions on Multimedia, 2020.

[2] M. Zhang, Y. Wang, P. Kadam, S. Liu, and C.-C. J. Kuo, “Pointhop++: A lightweight learning model on point sets for 3d classification,” arXiv preprint arXiv:2002.03281, 2020.

[3] M. Zhang, P. Kadam, S. Liu, and C.-C. J. Kuo, “Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentation.” arXiv preprint arXiv:2009.01280, 2020.