lucidrains/point-transformer-pytorch
A PyTorch implementation of the Point Transformer self-attention layer for 3D point cloud processing.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of the Point Transformer layer, based on a 2020 arXiv paper. The layer implements vector attention specifically designed for point cloud data, enabling tasks like classification and segmentation. It supports configurable hidden dimensions for position and attention MLPs, and optional k-nearest neighbor constraints to reduce computational cost by limiting attention to nearby points.
Frequently asked
- What is lucidrains/point-transformer-pytorch?
- A PyTorch implementation of the Point Transformer self-attention layer for 3D point cloud processing.
- Is point-transformer-pytorch open source?
- Yes — lucidrains/point-transformer-pytorch is open source, released under the MIT license.
- What language is point-transformer-pytorch written in?
- lucidrains/point-transformer-pytorch is primarily written in Python.
- How popular is point-transformer-pytorch?
- lucidrains/point-transformer-pytorch has 600 stars on GitHub.
- Where can I find point-transformer-pytorch?
- lucidrains/point-transformer-pytorch is on GitHub at https://github.com/lucidrains/point-transformer-pytorch.