aiqbench analysis
This research introduces a two-stream attention framework designed to address high-dimensional heterogeneity and class imbalance in airborne multispectral point clouds for land-cover classification. By fusing global spectral features with spectral-guided geometric features, the model demonstrates improved representation capabilities over existing state-of-the-art methods on two new datasets. The work offers a practical architectural approach for handling complex spatial-spectral data, with code and datasets planned for open release.
An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification
arXiv:2606.09123v1 Announce Type: cross Abstract: Multispectral point cloud (MPC) is composed of 3D spatial-spectral information, which holds tremendous potential for accurate land-cover classification. However, the representation power of classification models is limited by inherent high-dimensional and heterogeneous spatial-spectral information, unbalanced sample distribution, and inter-class spectral similarity of airborne MPCs. We build two MPC datasets and propose an enhanced geometric-spectral feature learning framework based on attentions for airborne MPC classification. A key component in our model is a two-stream feature fusion method with attention mechanisms, which enhances the representation capability of spatial-spectral features from high-dimensional heterogeneous MPCs. The first stream aims to extract position-encoded global spectral features with fusion self-attention, and the second stream comprises a multikernel point convolution and feature aggregation attention to extract spectral-guided geometric features. We then develop a residual attention fusion block to integrate the most informative geometric-spectral features from the two parallel streams. Another important contribution of this work is a joint loss function to improve the learning ability on unbalanced and interclass similar samples. Experimental results on two airborne MPC datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods. Furthermore, the codes and datasets used in this paper will be made available freely at https://github.com/HITlixian/TGRS_GSFF.
Abstract:Multispectral point cloud (MPC) is composed of 3D spatial-spectral information, which holds tremendous potential for accurate land-cover classification. However, the representation power of classification models is limited by inherent high-dimensional and heterogeneous spatial-spectral information, unbalanced sample distribution, and inter-class spectral similarity of airborne MPCs. We build two MPC datasets and propose an enhanced geometric-spectral feature learning framework based on attentions for airborne MPC classification. A key component in our model is a two-stream feature fusion method with attention mechanisms, which enhances the representation capability of spatial-spectral features from high-dimensional heterogeneous MPCs. The first stream aims to extract position-encoded global spectral features with fusion self-attention, and the second stream comprises a multikernel point convolution and feature aggregation attention to extract spectral-guided geometric features. We then develop a residual attention fusion block to integrate the most informative geometric-spectral features from the two parallel streams. Another important contribution of this work is a joint loss function to improve the learning ability on unbalanced and interclass similar samples. Experimental results on two airborne MPC datasets demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods. Furthermore, the codes and datasets used in this paper will be made available freely at this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2606.09123 [cs.CV]
(or arXiv:2606.09123v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.09123 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 301 words
Related coverage
An Enhanced Geometric-Spectral Feature Learning Framework for Airborne Multispectral Point Cloud Classification
arXiv · Aug 6, 2026
Dual-Domain Manifold Modeling for Hyperspectral Image Fusion
arXiv · Jul 29, 2026
RoofSeg: An edge-aware transformer-based network for end-to-end roof plane segmentation
arXiv · Sep 16, 2026
SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning
arXiv · Jun 4, 2026