mlsanityData to 14 Oct 2026

3D Object Detection with Pointformer

arXiv 2012.11409 ↗First posted 21 Dec 2020cs.CVcited by 194

Not on the map. Why?

Abstract (arXiv)

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features effectively. Specifically, a Local Transformer module is employed to model interactions among points in a local region, which learns context-dependent region features at an object level. A Global Transformer is designed to learn context-aware representations at the scene level. To further capture the dependencies among multi-scale representations, we propose Local-Global Transformer to integrate local features with global features from higher resolution. In addition, we introduce an efficient coordinate refinement module to shift down-sampled points closer to object centroids, which improves object proposal generation. We use Pointformer as the backbone for state-of-the-art object detection models and demonstrate significant improvements over original models on both indoor and outdoor datasets.

Key facts. Cited by 194 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 22; 2022: 66; 2023: 51; 2024: 28; 2025: 19; 2026: 8.

194 papers.

Sort:

By area:

  1. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  2. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  3. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 303
  4. 2022Vision Transformer with Deformable Attentioncited by 295
  5. 2021Voxel Transformer for 3D Object Detectioncited by 247
  6. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  7. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
  8. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  9. 2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
  10. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  11. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  12. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
38 more
  1. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  2. 2021A Survey of Visual Transformerscited by 117
  3. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  4. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  5. 2022Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Cloudscited by 102
  6. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  7. 2022InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understandingcited by 89
  8. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  9. 2023Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformerscited by 81
  10. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  11. 2021On the Integration of Self-Attention and Convolutioncited by 74
  12. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 73
  13. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 72
  14. 2022Point Density-Aware Voxels for LiDAR 3D Object Detectioncited by 70
  15. 2023E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuningcited by 70
  16. 2023MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Drivingcited by 68
  17. 2022Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstructioncited by 67
  18. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 67
  19. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  20. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  21. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  22. 2022NeRF-RPN: A general framework for object detection in NeRFscited by 46
  23. 2021Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphscited by 44
  24. 2022Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysiscited by 44
  25. 2022PointAttN: You Only Need Attention for Point Cloud Completioncited by 44
  26. 20223D Siamese Transformer Network for Single Object Tracking on Point Cloudscited by 44
  27. 2023UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye Viewcited by 43
  28. 2022Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Cloudscited by 39
  29. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  30. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  31. 2023Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attentioncited by 38
  32. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  33. 2023Attention-based Point Cloud Edge Samplingcited by 37
  34. 2022D-Former: A U-shaped Dilated Transformer for 3D Medical Image Segmentationcited by 35
  35. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  36. 2022Contrastive Language-Image Pre-Training with Knowledge Graphscited by 34
  37. 2022A Unified Query-based Paradigm for Point Cloud Understandingcited by 32
  38. 2022CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detectioncited by 32

50 most cited of 194 All 194 (JSON)