We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use lattice-based methods to process and learn 3D spatial information; however, this leads to inevitable discretization errors. In this work, we handle raw 3D points without such compromise. The proposed networks follow the autoencoder framework with a focus on designing the decoder. The encoder adopts similar architectures as in PointNet. The decoder involves three novel modules. The folding module folds a canonical 2D lattice to the underlying surface of a 3D point cloud, achieving coarse reconstruction; the graph-topology-inference module learns a graph topology to represent pairwise relationships between 3D points, pushing the latent code to preserve both coordinates and pairwise relationships of points in 3D point clouds; and the graph-filtering module couples the above two modules, refining the coarse reconstruction through a learnt graph topology to obtain the final reconstruction. The proposed decoder leverages a learnable graph topology to push the codeword to preserve representative features and further improve the unsupervised-learning performance. We further provide theoretical analyses of the proposed architecture. In the experiments, we validate the proposed networks in three tasks, including 3D point cloud reconstruction, visualization, and transfer classification. The experimental results show that (1) the proposed networks outperform the state-of-the-art methods in various tasks; (2) a graph topology can be inferred as auxiliary information without specific supervision on graph topology inference; and (3) graph filtering refines the reconstruction, leading to better performances.
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering
Research Paper / Nov 2019
Related Content
White Paper /May 2025
Media over Wireless: Networks for Ubiquitous Video
Research Paper /Mar 2025
To realize the objectives of Integrated Sensing and
Communication (ISAC) in 6G, there is a need to introduce
new functionalities in 6G core (6GC) architecture that are
dynamic and resource-efficient. In ISAC, sensing signals are used by a Sensing Receiver (SRx) to measure and report Sensing Data Points (SDPs) to the network. However, a direct approach involving …
Research Paper /Mar 2025
This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Compression for Machines (FCM).
This standard aims at providing inter-operable compressed bitstreams of features in the context of split computing, i.e., when the inference of a large computer vision Neural-Netwo…
Webinar /Jun 2024
Blog Post /Jun 2025
Blog Post /Jun 2025