CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding

Fei Wang

doi:10.7717/peerj-cs.3194

CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding

2025-09-19

0

OA

AI

DOI：10.7717/peerj-cs.3194

Original

Original request for help

Save

Abstract

En 中文

We propose a self-supervised point cloud representation learning framework CrossAlignNet based on cross-modal mask alignment strategy, to solve the problems of imbalance between global semantic and local geometric feature learning, as well as cross-modal information asymmetry in existing methods. A geometrically consistent mask region is established between the point cloud patches and the corresponding image patches through a synchronized mask alignment strategy to ensure cross-modal information symmetry. A dual-task learning framework is designed: the global semantic alignment task enhances the cross-modal semantic consistency through contrastive learning, and the local mask reconstruction task fuses the image cues using the cross-attention mechanism to recover the local geometric structure of the masked point cloud. In addition, the ShapeNet3D-CMA dataset is constructed to provide accurate point cloud-image spatial mapping relations to support cross-modal learning. Our framework shows superior or comparative results against existing methods on three point cloud understanding tasks including object classification, few-shot classification, and part segmentation.

Keywords:

Point cloud

Self-supervised learning

Feature learning

3D object classification

CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding

Abstract

Journal

Organization