Liu, Y., Yan, X., Li, Z., Chen, Z., Wei, Z. and Wei, M., 2023. PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Clouds. IEEE Transactions on Geoscience and Remote Sensing, 61, 5705312.
Full text available as:
![]() |
PDF
PointGame_arxiv.pdf - Accepted Version Restricted to Repository staff only until 9 November 2025. Available under License Creative Commons Attribution Non-commercial. 10MB |
Copyright to original material in this document is with the original owner(s). Access to this content through BURO is granted on condition that you use it only for research, scholarly or other non-commercial purposes. If you wish to use it for any other purposes, you must contact BU via BURO@bournemouth.ac.uk. Any third party copyright material in this document remains the property of its respective owner(s). BU grants no licence for further use of that third party material. |
DOI: 10.1109/TGRS.2023.3331748
Abstract
Self-supervised learning is attracting large attention in point cloud understanding. However, exploring discriminative and transferable features still remains challenging due to their nature of irregularity. We propose a geometrically and adaptively masked auto-encoder on point clouds for self-supervised learning, termed <italic>PointGame</italic>. PointGame contains two core components: GATE and EAT. GATE stands for the geometrical and adaptive token embedding module; it not only absorbs the conventional wisdom of geometric descriptors that captures the surface shape effectively, but also exploits adaptive saliency to focus on the salient part of a point cloud. EAT stands for the external attention-based Transformer encoder with linear computational complexity, which increases the efficiency of the whole pipeline. Unlike cutting-edge unsupervised learning models, PointGame leverages geometric descriptors to perceive surface shapes and adaptively mines discriminative features from training data. PointGame showcases clear advantages over its competitors on various downstream tasks under both global and local fine-tuning strategies. The code and pre-trained models will be publicly available.
Item Type: | Article |
---|---|
ISSN: | 0196-2892 |
Uncontrolled Keywords: | Point cloud compression; Feature extraction; Three-dimensional displays; Task analysis; Transformers; Representation learning; Shape; Geometric descriptors; geometrical and adaptive token embedding (GATE); masked autoencoder; representation learning; self-supervised learning |
Group: | Faculty of Media & Communication |
ID Code: | 39219 |
Deposited By: | Symplectic RT2 |
Deposited On: | 04 Dec 2023 10:32 |
Last Modified: | 04 Dec 2023 10:32 |
Downloads
Downloads per month over past year
Repository Staff Only - |