CA-Net : a context-awareness and cross-channel attention-based network for point cloud understanding

Lin, Junting and Zou, Jiping and Chen, (Ken) and Chai, Jinchuan and Zuo, Jing (2025) CA-Net : a context-awareness and cross-channel attention-based network for point cloud understanding. Measurement Science and Technology, 36. 045207. ISSN 0957-0233 (https://doi.org/10.1088/1361-6501/adc029)

[thumbnail of 2025_Lin_etal_MS_T_CA-Net_A_Context_Aware_and_Cross-Channel_Attention_Encoder_for_Point_Cloud_Understanding]
Preview
Text. Filename: 2025_Lin_etal_MS_T_CA-Net_A_Context_Aware_and_Cross-Channel_Attention_Encoder_for_Point_Cloud_Understanding_1_.pdf
Accepted Author Manuscript
License: Creative Commons Attribution 4.0 logo

Download (2MB)| Preview

Abstract

To capture local complex shape information and fine-grained features from irregular point cloud, this paper proposes a novel local feature encoder-based network named CA-Net which is used to solve the challenge of 3D object classification and segmentation. The core of the CA-Net is CA-Encoder, which is based on context-awareness (CA) and cross-channel multi-head self-attention (CC-MSA). CA-Encoder uses contextual information awareness to aggregate local features from two levels: point cloud 3D coordinate information and high-dimensional implicitly encoded information, leveraging CC-MSA to learn channel-related information. For different point cloud benchmark tasks, CA-Net uses the local feature enhancement module (classification) and the Up-Transformer (segmentation) which includes a cascaded set of CA-Encoders to solve the problem of feature loss at non-edge points in edge sampling, so that the sampled results can both preserve the shape of the point cloud edges and reconstruct the full internal shape structure of the point cloud. The CA-Net has superior performance in experiments on ModelNet and ShapeNetPart datasets with a classification accuracy of 93.8% and a segmentation accuracy of 85.9%.

ORCID iDs

Lin, Junting, Zou, Jiping, Chen, (Ken) ORCID logoORCID: https://orcid.org/0000-0002-6093-6623, Chai, Jinchuan and Zuo, Jing;