TY - JOUR
T1 - Context-based local-global fusion network for 3D point cloud classification and segmentation
AU - Wu, Junwei
AU - Sun, Mingjie
AU - Jiang, Chenru
AU - Liu, Jiejie
AU - Smith, Jeremy
AU - Zhang, Quan
N1 - Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/10/1
Y1 - 2024/10/1
N2 - 3D point clouds have gained much research attention because of their ability to represent the spatial information of real-world environments in a detailed manner. Despite recent progress in point cloud processing with deep neural networks, most of them either implement sophisticated local feature aggregation methods or imitate 2D convolution operations in the range of K nearest neighbors with limited local context information. These methods may struggle to distinguish between similar geometric shapes within the local region of K nearest neighbors, such as doors and walls. To address this issue, we propose a novel local–global fusion network that captures the diverse local geometric shapes with global structure information. The proposed local–global fusion network comprises two main modules. Firstly, we have developed an effective approach for local context learning using incremental dilated KNN (IDKNN) as the neighbor selecting mechanism to enlarge the receptive field and incorporate more reliable points for local geometric shape learning. Secondly, a three-direction region-wise spatial attention (TRSA) algorithm has been developed to explore the global contextual dependencies. For global context learning, we first split the entire 3D space into regions with equal numbers of points, and, then, intra-region context features are extracted to learn the inter-region relations from three orthogonal directions, taking global structural knowledge into account. By fusing the local context information and global contextual dependencies, we establish a Local-Global Fusion Network, end-to-end framework, called LGFNet. Extensive experimental results on several benchmark datasets clearly demonstrate our approach can achieve state-of-the-art (SOTA) performance on point cloud classification, part segmentation, and indoor semantic segmentation. In addition, TRSA and IKDNN can be easily used in a plug-and-play fashion with various existing SOTA networks to substantially improve their performance. Our code is available at https://github.com/jasonwjw/IDKNN
AB - 3D point clouds have gained much research attention because of their ability to represent the spatial information of real-world environments in a detailed manner. Despite recent progress in point cloud processing with deep neural networks, most of them either implement sophisticated local feature aggregation methods or imitate 2D convolution operations in the range of K nearest neighbors with limited local context information. These methods may struggle to distinguish between similar geometric shapes within the local region of K nearest neighbors, such as doors and walls. To address this issue, we propose a novel local–global fusion network that captures the diverse local geometric shapes with global structure information. The proposed local–global fusion network comprises two main modules. Firstly, we have developed an effective approach for local context learning using incremental dilated KNN (IDKNN) as the neighbor selecting mechanism to enlarge the receptive field and incorporate more reliable points for local geometric shape learning. Secondly, a three-direction region-wise spatial attention (TRSA) algorithm has been developed to explore the global contextual dependencies. For global context learning, we first split the entire 3D space into regions with equal numbers of points, and, then, intra-region context features are extracted to learn the inter-region relations from three orthogonal directions, taking global structural knowledge into account. By fusing the local context information and global contextual dependencies, we establish a Local-Global Fusion Network, end-to-end framework, called LGFNet. Extensive experimental results on several benchmark datasets clearly demonstrate our approach can achieve state-of-the-art (SOTA) performance on point cloud classification, part segmentation, and indoor semantic segmentation. In addition, TRSA and IKDNN can be easily used in a plug-and-play fashion with various existing SOTA networks to substantially improve their performance. Our code is available at https://github.com/jasonwjw/IDKNN
KW - Context learning
KW - Global attention
KW - Local-global fusion
KW - Point cloud
UR - http://www.scopus.com/inward/record.url?scp=85191610480&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2024.124023
DO - 10.1016/j.eswa.2024.124023
M3 - Article
AN - SCOPUS:85191610480
SN - 0957-4174
VL - 251
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 124023
ER -