mlsanityData to 7 Oct 2026

CenterFormer: Center-based Transformer for 3D Object Detection

arXiv 2209.05588 ↗First posted 12 Sep 2022cs.CVcited by 99

Not on the map. Why?

Abstract (arXiv)

Query-based transformer has shown great potential in constructing long-range attention in many image-domain tasks, but has rarely been considered in LiDAR-based 3D object detection due to the overwhelming size of the point cloud data. In this paper, we propose CenterFormer, a center-based transformer network for 3D object detection. CenterFormer first uses a center heatmap to select center candidates on top of a standard voxel-based point cloud encoder. It then uses the feature of the center candidate as the query embedding in the transformer. To further aggregate features from multiple frames, we design an approach to fuse features through cross-attention. Lastly, regression heads are added to predict the bounding box on the output center feature representation. Our design reduces the convergence difficulty and computational complexity of the transformer structure. The results show significant improvements over the strong baseline of anchor-free object detection networks. CenterFormer achieves state-of-the-art performance for a single model on the Waymo Open Dataset, with 73.7% mAPH on the validation set and 75.6% mAPH on the test set, significantly outperforming all previously published CNN and transformer-based methods. Our code is publicly available at https://github.com/TuSimple/centerformer

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). Builds on 61 of its 65 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

61 of 65 references.

References · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  10. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
38 more
  1. 2017Deformable Convolutional Networkscited by 1,481
  2. 2020Point Transformercited by 1,462
  3. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  6. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  11. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  12. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  13. 2021Conditional DETR for Fast Training Convergencecited by 422
  14. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  15. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  16. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  17. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  18. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  19. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  20. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  21. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 274
  22. 2021Voxel Transformer for 3D Object Detectioncited by 247
  23. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  24. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 231
  25. 2021Group-Free 3D Object Detection via Transformerscited by 215
  26. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  27. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  28. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  29. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  30. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  31. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  32. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  33. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  34. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  35. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  36. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  37. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  38. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 40; 2024: 32; 2025: 16; 2026: 7.

99 papers.

Sort:

By area:

  1. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  2. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  3. 2023SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detectioncited by 83
  4. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  5. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  6. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  7. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  8. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  9. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  10. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  11. 2023Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perceptioncited by 52
  12. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 52
38 more
  1. 2024SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detectioncited by 52
  2. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  3. 2023SAM3D: Zero-Shot 3D Object Detection via Segment Anything Modelcited by 40
  4. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  5. 2023BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detectioncited by 35
  6. 2023Super Sparse 3D Object Detectioncited by 32
  7. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  8. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  9. 2023SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusioncited by 30
  10. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  11. 2023Uni3DETR: Unified 3D Detection Transformercited by 26
  12. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  13. 2023Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detectioncited by 24
  14. 2022ConQueR: Query Contrast Voxel-DETR for 3D Object Detectioncited by 21
  15. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  16. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  17. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  18. 2024Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehensioncited by 17
  19. 2023MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequencescited by 15
  20. 2023MACP: Efficient Model Adaptation for Cooperative Perceptioncited by 14
  21. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  22. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
  23. 2024An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domainscited by 10
  24. 2022Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancementcited by 9
  25. 2023PARTNER: Level up the Polar Representation for LiDAR 3D Object Detectioncited by 9
  26. 2025FSHNet: Fully Sparse Hybrid Network for 3D Object Detectioncited by 9
  27. 2023Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detectioncited by 8
  28. 2023PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detectioncited by 8
  29. 2024GestFormer: Multiscale Wavelet Pooling Transformer Network for Dynamic Hand Gesture Recognitioncited by 7
  30. 2024Towards Stable 3D Object Detectioncited by 7
  31. 2023ParisLuco3D: A high-quality target dataset for domain generalization of LiDAR perceptioncited by 5
  32. 2023FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusioncited by 5
  33. 2024Weak-to-Strong 3D Object Detection with X-Ray Distillationcited by 5
  34. 2025INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomycited by 5
  35. 2024Small, Versatile and Mighty: A Range-View Perception Frameworkcited by 4
  36. 2024PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interestcited by 4
  37. 2023Efficient Transformer-based 3D Object Detection with Dynamic Token Haltingcited by 3
  38. 2024MsSVT++: Mixed-scale Sparse Voxel Transformer with Center Voting for 3D Object Detectioncited by 3

50 most cited of 99 All 99 (JSON)