Skip to main content

DHGCN: Dynamic hop graph convolution network for self-supervised point cloud learning.

Jiang, J., Zhao, L., Lu, X., Hu, W., Razzak, I. and Wang, M., 2024. DHGCN: Dynamic hop graph convolution network for self-supervised point cloud learning. In: The 38th Annual AAAI Conference on Artificial Intelligence, 22-25 February 2024, Vancouver, Canada.

Full text available as:

AAAI24_DHGCN_camera_ready.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


Official URL:


Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting local features through GCNs, while ignoring the relationship between point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between the voxelized point parts, which are treated as graph nodes. Motivated by the intuition that the contextual information between point parts lies in the pairwise adjacent relationship, which can be depicted by the hop distance of the graph quantitatively, we devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. In addition, we propose the Hop Graph Attention (HGA), which takes the learned hop distance as input for producing attention weights to allow edge features to contribute distinctively in aggregation. Eventually, the proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks. Comprehensive experiments on different backbones and tasks demonstrate that our self-supervised method achieves state-of-the-art performance. Our source code is available at:

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:40079
Deposited By: Symplectic RT2
Deposited On:10 Jul 2024 11:53
Last Modified:10 Jul 2024 11:53


Downloads per month over past year

More statistics for this item...
Repository Staff Only -