mlsanityData to 7 Oct 2026

Embracing Single Stride 3D Object Detector with Sparse Transformer

arXiv 2112.06375 ↗First posted 13 Dec 2021cs.CVcited by 193

Not on the map. Why?

Abstract (arXiv)

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL 1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Codes will be released at https://github.com/TuSimple/SST

Key facts. Cited by 193 papers in the map (data through 7 Oct 2026). Builds on 65 of its 75 references that are in the map. First posted on arXiv 13 Dec 2021.

Builds on

65 of 75 references.

References · 65

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  12. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
38 more
  1. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  4. 2020Point Transformercited by 1,462
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 849
  13. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  14. 2020PCT: Point cloud transformercited by 730
  15. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  16. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  17. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  18. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  19. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  20. 2015Attention-Based Models for Speech Recognitioncited by 400
  21. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  22. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  23. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  24. 2020Exploring Self-attention for Image Recognitioncited by 313
  25. 2021Voxel Transformer for 3D Object Detectioncited by 247
  26. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  27. 2017Submanifold Sparse Convolutional Networkscited by 223
  28. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 206
  29. 20203D Object Detection with Pointformercited by 194
  30. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  31. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  32. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  33. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  34. 2019Learning Data Augmentation Strategies for Object Detectioncited by 139
  35. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  36. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  37. 2017DSSD : Deconvolutional Single Shot Detectorcited by 130
  38. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 32; 2023: 62; 2024: 55; 2025: 29; 2026: 15.

193 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Drivingcited by 233
  3. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  4. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  5. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  8. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  9. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  10. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  11. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  12. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
38 more
  1. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  2. 2022Fully Sparse 3D Object Detectioncited by 84
  3. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  4. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  5. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  6. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  7. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 71
  8. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  9. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  10. 2022CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Cloudscited by 58
  11. 2023FocalFormer3D : Focusing on Hard Instance for 3D Object Detectioncited by 58
  12. 2022Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoderscited by 57
  13. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  14. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  15. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  16. 2022Learning for Vehicle-to-Vehicle Cooperative Perception under Lossy Communicationcited by 47
  17. 2023HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Cloudscited by 45
  18. 2024RangeLDM: Fast Realistic LiDAR Point Cloud Generationcited by 45
  19. 2022Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Cloudscited by 39
  20. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  21. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 39
  22. 2023GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Trainingcited by 38
  23. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  24. 2023FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxelscited by 34
  25. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  26. 2022LidarCLIP or: How I Learned to Talk to Point Cloudscited by 33
  27. 2023MUVO: A Multimodal Generative World Model for Autonomous Driving with Geometric Representationscited by 33
  28. 2024GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detectioncited by 33
  29. 2023Super Sparse 3D Object Detectioncited by 32
  30. 2023OcTr: Octree-based Transformer for 3D Object Detectioncited by 32
  31. 2023Fully Sparse Fusion for 3D Object Detectioncited by 29
  32. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  33. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  34. 2023Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detectioncited by 28
  35. 2023Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labelingcited by 28
  36. 2022Densely Constrained Depth Estimator for Monocular 3D Object Detectioncited by 27
  37. 2025OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generationcited by 27
  38. 2023MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Trainingcited by 26

50 most cited of 193 All 193 (JSON)