Point cloud sampling is a less explored research topic for this data representation. The most
commonly used sampling methods are still classical random sampling and farthest point …

In the field of deep point cloud understanding KPConv is a unique architecture that uses
kernel points to locate convolutional weights in space instead of relying on Multi-Layer …

Contrastive learning is an essential method in self-supervised learning. It primarily employs
a multi-branch strategy to compare latent representations obtained from different branches …

Point cloud segmentation is one of the most important tasks in LiDAR remote sensing with
widespread scientific, industrial, and commercial applications. The research thereof has …

Transformer networks have demonstrated remarkable performance in point cloud analysis.
However, achieving a balance between local regional context and global long-range context …

Inspired by classical works, when constructing local relationships in point clouds, there is
always a geometric description of the central point and its neighboring points. However, the …

Transformer networks have demonstrated remarkable performance in point cloud
processing tasks. However, balancing local feature aggregation with long-range …

This paper applied a transformer based deep learning model 3D Point Cloud Transformer
(3DPCT) to conduct a tree species classification of Airborne LiDAR data. There are a total …

Transformer has become a widely used deep learning model in Computer Vision
applications, alongside Convolutional Neural Networks. Its ability to capture long-term …