JIA-Lab-research/Stratified-Transformer
A Transformer-based method for 3D point cloud semantic segmentation that achieves state-of-the-art performance on S3DIS and ScanNetv2 datasets.
Not currently ranked — collecting fresh signals.
star history
This repository provides the official PyTorch implementation of Stratified Transformer, a point-based approach to 3D point cloud semantic segmentation that uses standard multi-head self-attention to achieve a large receptive field and robust generalization. The method is notable as the first point-based approach to outperform voxel-based methods like SparseConvNet and MinkowskiNet. It includes memory-efficient CUDA kernels to handle variable-length tokens with shared memory acceleration.
Frequently asked
- What is JIA-Lab-research/Stratified-Transformer?
- A Transformer-based method for 3D point cloud semantic segmentation that achieves state-of-the-art performance on S3DIS and ScanNetv2 datasets.
- Is Stratified-Transformer open source?
- Yes — JIA-Lab-research/Stratified-Transformer is open source, released under the MIT license.
- What language is Stratified-Transformer written in?
- JIA-Lab-research/Stratified-Transformer is primarily written in Python.
- How popular is Stratified-Transformer?
- JIA-Lab-research/Stratified-Transformer has 432 stars on GitHub.
- Where can I find Stratified-Transformer?
- JIA-Lab-research/Stratified-Transformer is on GitHub at https://github.com/JIA-Lab-research/Stratified-Transformer.