2-s3net: Attentive feature fusion with adaptive feature selection for sparse semantic segmentation network
Autonomous robotic systems and self driving cars rely on accurate perception of their
surroundings as the safety of the passengers and pedestrians is the top priority. Semantic …
surroundings as the safety of the passengers and pedestrians is the top priority. Semantic …
[HTML][HTML] AGFP-Net: Attentive geometric feature pyramid network for land cover classification using airborne multispectral LiDAR data
Accurate land cover (LC) classification plays an important role in ecosystem protection,
climate changes, and urban planning. The airborne multispectral LiDAR data are …
climate changes, and urban planning. The airborne multispectral LiDAR data are …
[HTML][HTML] Building extraction from airborne multi-spectral LiDAR point clouds based on graph geometric moments convolutional neural networks
Building extraction has attracted much attentions for decades as a prerequisite for many
applications and is still a challenging topic in the field of photogrammetry and remote …
applications and is still a challenging topic in the field of photogrammetry and remote …
Few-shot shape recognition by learning deep shape-aware features
Traditional shape descriptors have been gradually replaced by convolutional neural
networks due to their superior performance in feature extraction and classification. The state …
networks due to their superior performance in feature extraction and classification. The state …
[HTML][HTML] Graph Neural Networks in Point Clouds: A Survey
D Li, C Lu, Z Chen, J Guan, J Zhao, J Du - Remote Sensing, 2024 - mdpi.com
With the advancement of 3D sensing technologies, point clouds are gradually becoming the
main type of data representation in applications such as autonomous driving, robotics, and …
main type of data representation in applications such as autonomous driving, robotics, and …
[HTML][HTML] A 3D Point Cloud Classification Method Based on Adaptive Graph Convolution and Global Attention
Y Yue, X Li, Y Peng - Sensors, 2024 - mdpi.com
In recent years, there has been significant growth in the ubiquity and popularity of three-
dimensional (3D) point clouds, with an increasing focus on the classification of 3D point …
dimensional (3D) point clouds, with an increasing focus on the classification of 3D point …
Higher-order graph convolutional networks with multi-scale neighborhood pooling for semi-supervised node classification
X Liu, G Xia, F Lei, Y Zhang, S Chang - IEEE Access, 2021 - ieeexplore.ieee.org
Existing popular methods for semi-supervised node classification with high-order
convolution improve the learning ability of graph convolutional networks (GCNs) by …
convolution improve the learning ability of graph convolutional networks (GCNs) by …
Physics-Informed Geometric Operators to Support Surrogate, Dimension Reduction and Generative Models for Engineering Design
In this work, we propose a set of physics-informed geometric operators (GOs) to enrich the
geometric data provided for training surrogate/discriminative models, dimension reduction …
geometric data provided for training surrogate/discriminative models, dimension reduction …
SMA-Net: Deep learning-based identification and fitting of CAD models from point clouds
Identification and fitting is an important task in reverse engineering and virtual/augmented
reality. Compared to the traditional approaches, carrying out such tasks with a deep learning …
reality. Compared to the traditional approaches, carrying out such tasks with a deep learning …
Multi-head self-attention for 3D point Cloud classification
XY Gao, YZ Wang, CX Zhang, JQ Lu - IEEE Access, 2021 - ieeexplore.ieee.org
3D point cloud classification is a hot issue in recent years. 3D point cloud is different from
regular data such as image and text. Disorder of point cloud makes two-dimensional (2D) …
regular data such as image and text. Disorder of point cloud makes two-dimensional (2D) …