mlsanityData to 13 Oct 2026

Point Transformer

arXiv 2011.00931 ↗First posted 2 Nov 2020cs.CVcited by 1,465

Not on the map. Why?

Cited by 53 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets. We design Point Transformer to extract local and global features and relate both representations by introducing the local-global attention mechanism, which aims to capture spatial point relations and shape information. For that purpose, we propose SortNet, as part of the Point Transformer, which induces input permutation invariance by selecting points based on a learned score. The output of Point Transformer is a sorted and permutation invariant feature list that can directly be incorporated into common computer vision applications. We evaluate our approach on standard classification and part segmentation benchmarks to demonstrate competitive results compared to the prior work. Code is publicly available at: https://github.com/engelnico/point-transformer

Key facts. Cited by 1,465 papers in the map (data through 13 Oct 2026). First posted on arXiv 2 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 114; 2022: 227; 2023: 303; 2024: 304; 2025: 302; 2026: 215.

1,465 papers.

Sort:

By area:

  1. 2021ViViT: A Video Vision Transformercited by 1,615
  2. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  3. 2021Transformers in Vision: A Surveycited by 1,010
  4. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  5. 2021Multiscale Vision Transformerscited by 896
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 859
  7. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 852
  8. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 715
  9. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 648
  10. 2023Point Transformer V3: Simpler, Faster, Strongercited by 584
  11. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  12. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 457
38 more
  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 452
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  3. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 428
  4. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 385
  5. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  6. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  7. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 313
  8. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 300
  9. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  10. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  11. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 265
  12. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  13. 2021Voxel Transformer for 3D Object Detectioncited by 247
  14. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  15. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 234
  16. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  17. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 224
  18. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
  19. 2021FaceFormer: Speech-Driven 3D Facial Animation with Transformerscited by 208
  20. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  21. 2022Geometric Transformer for Fast and Robust Point Cloud Registrationcited by 201
  22. 2021Anticipative Video Transformercited by 199
  23. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  24. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  25. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 195
  26. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  27. 2021Chasing Sparsity in Vision Transformers: An End-to-End Explorationcited by 181
  28. 2021Adaptive Token Sampling For Efficient Vision Transformerscited by 180
  29. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 177
  30. 2024Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoningcited by 172
  31. 2021SPViT: Enabling Faster Vision Transformers via Soft Token Pruningcited by 166
  32. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  33. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  34. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 163
  35. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  36. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  37. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  38. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 157

50 most cited of 1,465 All 1,465 (JSON)