mlsanityData to 14 Oct 2026

EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation

arXiv 2512.00385 ↗First posted 29 Nov 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Superpoint-based pipelines provide an efficient alternative to point- or voxel-based 3D semantic segmentation, but are often bottlenecked by their CPU-bound partition step. We propose a learnable, fully GPU partitioning algorithm that generates geometrically and semantically coherent superpoints 13× faster than prior methods. Our module is compact (under 60k parameters), trains in under 20 minutes with a differentiable surrogate loss, and requires no handcrafted features. Combine with a lightweight superpoint classifier, the full pipeline fits in <2 MB of VRAM, scales to multi-million-point scenes, and supports real-time inference. With 72× faster inference and 120× fewer parameters, EZ-SP matches the accuracy of point-based SOTA models across three domains: indoor scans (S3DIS), autonomous driving (KITTI-360), and aerial LiDAR (DALES). Code and pretrained models are accessible at github.com/drprojects/superpointtransformer.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 29 Nov 2025.

Builds on

38 of 61 references.

References · 38

  1. 2023Segment Anythingcited by 8,234
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  4. 2020Point Transformercited by 1,470
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2020PCT: Point cloud transformercited by 732
  9. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  10. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  12. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
26 more
  1. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  2. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  3. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  4. 2023SAM3D: Segment Anything in 3D Scenescited by 157
  5. 2022Superpoint Transformer for 3D Scene Instance Segmentationcited by 116
  6. 2021Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networkscited by 99
  7. 2022REGTR: End-to-end Point Cloud Correspondences with Transformerscited by 96
  8. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  9. 2020DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentationcited by 66
  10. 2023Efficient 3D Semantic Segmentation with Superpoint Transformercited by 57
  11. 2019Point Cloud Oversegmentation with Graph-Structured Deep Metric Learningcited by 42
  12. 2023TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUscited by 36
  13. 2023SAM-guided Graph Cut for 3D Instance Segmentationcited by 35
  14. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  15. 2020Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Cloudscited by 23
  16. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  17. 2022Online Segmentation of LiDAR Sequences: Dataset and Algorithmcited by 14
  18. 2024Scalable 3D Panoptic Segmentation As Superpoint Graph Clusteringcited by 14
  19. 2024Multiway Point Cloud Mosaicking with Diffusion and Global Optimizationcited by 14
  20. 2024One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigationcited by 13
  21. 2020Cascaded Non-local Neural Network for Point Cloud Semantic Segmentationcited by 12
  22. 2023SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detectioncited by 11
  23. 2023Region-Enhanced Feature Learning for Scene Semantic Segmentationcited by 6
  24. 2017Graph Based Over-Segmentation Methods for 3D Point Cloudscited by 4
  25. 2019Parallel Cut Pursuit For Minimization of the Graph Total Variationcited by 4
  26. 2017Saliency-guided Adaptive Seeding for Supervoxel Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR datacited by 0
  2. 2026Toward a foundation model for forest point cloudscited by 0