# Efficient 3D Semantic Segmentation with Superpoint Transformer

arXiv: https://arxiv.org/abs/2306.08045 · HTML: https://mlsanity.com/paper/2306.08045/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 63 references that are in the map.
- First posted on arXiv 13 Jun 2023.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Graph U-Nets](https://mlsanity.com/paper/1905.05178/) (2019)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://mlsanity.com/paper/2003.06537/) (2020)
- [Stratified Transformer for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2203.14508/) (2022)
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2003.13867/) (2020)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training](https://mlsanity.com/paper/2009.03294/) (2020)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks](https://mlsanity.com/paper/2108.07478/) (2021)
- [Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding](https://mlsanity.com/paper/2105.12723/) (2021)

## Built on by (most cited first, 30 of 57)

- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [Sonata: Self-Supervised Learning of Reliable Point Representations](https://mlsanity.com/paper/2503.16429/) (2025)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration](https://mlsanity.com/paper/2502.16652/) (2025)
- [3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2308.16632/) (2023)
- [SAM-guided Graph Cut for 3D Instance Segmentation](https://mlsanity.com/paper/2312.08372/) (2023)
- [SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians](https://mlsanity.com/paper/2412.10231/) (2024)
- [LitePT: Lighter Yet Stronger Point Transformer](https://mlsanity.com/paper/2512.13689/) (2025)
- [Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering](https://mlsanity.com/paper/2401.06704/) (2024)
- [ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation](https://mlsanity.com/paper/2404.10699/) (2024)
- [PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests](https://mlsanity.com/paper/2404.12064/) (2024)
- [COS3D: Collaborative Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2510.20238/) (2025)
- [LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2506.07857/) (2025)
- [Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds](https://mlsanity.com/paper/2502.06227/) (2025)
- [Unsupervised semantic segmentation of urban high-density multispectral point clouds](https://mlsanity.com/paper/2410.18520/) (2024)
- [OE3DIS: Open-Ended 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/2408.11747/) (2024)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis](https://mlsanity.com/paper/2511.07823/) (2025)
- [3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation](https://mlsanity.com/paper/2504.12599/) (2025)
- [Cross-modal feature fusion for robust point cloud registration with ambiguous geometry](https://mlsanity.com/paper/2505.13088/) (2025)
- [HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning](https://mlsanity.com/paper/2507.19778/) (2025)
- [SGS-3D: High-Fidelity 3D Instance Segmentation via Reliable Semantic Mask Splitting and Growing](https://mlsanity.com/paper/2509.05144/) (2025)
- [TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding](https://mlsanity.com/paper/2511.07007/) (2025)
- [EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation](https://mlsanity.com/paper/2512.00385/) (2025)
- [3D Learnable Supertoken Transformer for LiDAR Point Cloud Scene Segmentation](https://mlsanity.com/paper/2405.15826/) (2024)
- [Exploring contextual modeling with linear complexity for point cloud segmentation](https://mlsanity.com/paper/2410.21211/) (2024)
- [CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization](https://mlsanity.com/paper/2501.13073/) (2025)
- [HyperPointFormer: Multimodal Fusion in 3D Space with Dual-Branch Cross-Attention Transformers](https://mlsanity.com/paper/2505.23206/) (2025)
- [SPPSFormer: High-quality Superpoint-based Transformer for Roof Plane Instance Segmentation from Point Clouds](https://mlsanity.com/paper/2505.24475/) (2025)

## Abstract (arXiv)

We introduce a novel superpoint-based transformer architecture for efficient semantic segmentation of large-scale 3D scenes. Our method incorporates a fast algorithm to partition point clouds into a hierarchical superpoint structure, which makes our preprocessing 7 times faster than existing superpoint-based approaches. Additionally, we leverage a self-attention mechanism to capture the relationships between superpoints at multiple scales, leading to state-of-the-art performance on three challenging benchmark datasets: S3DIS (76.0% mIoU 6-fold validation), KITTI-360 (63.5% on Val), and DALES (79.6%). With only 212k parameters, our approach is up to 200 times more compact than other state-of-the-art models while maintaining similar performance. Furthermore, our model can be trained on a single GPU in 3 hours for a fold of the S3DIS dataset, which is 7x to 70x fewer GPU-hours than the best-performing methods. Our code and models are accessible at github.com/drprojects/superpoint_transformer.