Multi-modal self-supervised contrastive representation learning for three-dimensional point cloud understanding

Open Webpage

Weichao Ding, Zehao Yang, Fei Luo, Chunhua Gu, Wenbo Dong

Published: 2025, Last Modified: 16 Oct 2025Eng. Appl. Artif. Intell. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Image and text modalities are used to enhance point cloud understanding.•The semantic bias among modalities is reduced by global feature and projection units.•Inter-modal and cross-modal contrastive learning better align multi-modal data.•Comprehensive experiments show that our algorithm outperforms other algorithms.