Point transformer (PT)
Point Transformer (PT) is a neural network architecture designed for processing 3D point cloud data. It leverages self-attention mechanisms to capture local and global geometric relationships within unordered point sets.
3D Deep Learning
RandLA-Net (efficient point cloud segmentation)
RandLA-Net is a deep learning architecture designed for efficient and scalable semantic segmentation of large-scale 3D point clouds. It employs random sampling and local feature aggregation to achieve high accuracy with reduced computational cost.
PointMLP (point cloud MLP)
PointMLP is a neural network architecture designed for processing three-dimensional point cloud data using multi-layer perceptrons (MLPs). It aims to efficiently capture local and global geometric features for tasks such as classification and segmentation in 3D vision applications.
PCT (point cloud transformer)
PCT (point cloud transformer) is a deep learning architecture designed to process and analyze 3D point cloud data using transformer mechanisms. It enables efficient feature extraction and understanding of spatial relationships in unstructured 3D data for various applications.
PointCNN
PointCNN is a convolutional neural network architecture designed specifically for processing point cloud data by learning an X-transformation to reorder and weight points before applying convolution.
Point cloud transformer
Point cloud transformers are a class of deep learning models designed to process and analyze 3D point cloud data using transformer architectures. They enable efficient feature extraction and global context modeling for tasks such as 3D object recognition and segmentation.