mlsanityData to 7 Oct 2026

FastPillars: A Deployment-friendly Pillar-based 3D Detector

arXiv 2302.02367 ↗First posted 5 Feb 2023cs.CV cs.ROcited by 39

Not on the map. Why?

Abstract (arXiv)

The deployment of 3D detectors strikes one of the major challenges in real-world self-driving scenarios. Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference, which puts a hard barrier for deployment, especially for on-device applications. In this paper, to tackle the challenge of efficient 3D object detection from an industry perspective, we devise a deployment-friendly pillar-based 3D detector, termed FastPillars. First, we introduce a novel lightweight Max-and-Attention Pillar Encoding (MAPE) module specially for enhancing small 3D objects. Second, we propose a simple yet effective principle for designing a backbone in pillar-based 3D detection. We construct FastPillars based on these designs, achieving high performance and low latency without SPConv. Extensive experiments on two large-scale datasets demonstrate the effectiveness and efficiency of FastPillars for on-device 3D detection regarding both performance and speed. Specifically, FastPillars delivers state-of-the-art accuracy on Waymo Open Dataset with 1.8X speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based). Our code is publicly available at: https://github.com/StiphyJay/FastPillars.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 56 of its 103 references that are in the map. First posted on arXiv 5 Feb 2023.

Builds on

56 of 103 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  12. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
38 more
  1. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  2. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  3. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  7. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  8. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  9. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  10. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  11. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  12. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  13. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  14. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  15. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  16. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  17. 2017Submanifold Sparse Convolutional Networkscited by 223
  18. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  19. 20203D Object Detection with Pointformercited by 194
  20. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  21. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  22. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  23. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  24. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  25. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  26. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  27. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  28. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  29. 2022Fully Sparse 3D Object Detectioncited by 84
  30. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  31. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  32. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  33. 2020SSN: Shape Signature Networks for Multi-class Object Detection from Point Cloudscited by 74
  34. 20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
  35. 2019What You See is What You Get: Exploiting Visibility for 3D Object Detectioncited by 69
  36. 2020LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attentioncited by 65
  37. 2021PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Cloudscited by 59
  38. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 11; 2025: 12; 2026: 14.

39 papers.

Sort:

By area:

  1. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 39
  2. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  3. 2026INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrievalcited by 26
  4. 2026HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrievalcited by 24
  5. 2026ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalcited by 15
  6. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  7. 2024MUFASA: Multi-View Fusion and Adaptation Network with Spatial Awareness for Radar Object Detectioncited by 13
  8. 2023PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detectioncited by 10
  9. 2024P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Cloudscited by 10
  10. 2024MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cuescited by 10
  11. 2025Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classificationcited by 10
  12. 2025CompTrack: Information Bottleneck-Guided Low-Rank Dynamic Token Compression for Point Cloud Trackingcited by 9
27 more
  1. 2026FocusTrack: One-Stage Focus-and-Suppress Framework for 3D Point Cloud Object Trackingcited by 7
  2. 2024A GEN AI Framework for Medical Note Generationcited by 6
  3. 2024GSRender: Deduplicated Occupancy Prediction via Weakly Supervised 3D Gaussian Splattingcited by 6
  4. 2023FusionViT: Hierarchical 3D Object Detection via LiDAR-Camera Vision Transformer Fusioncited by 5
  5. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  6. 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Modelscited by 4
  7. 2025Rethinking Backbone Design for Lightweight 3D Object Detection in LiDARcited by 3
  8. 2026FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Predictioncited by 3
  9. 2024PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Cloudscited by 2
  10. 2025LiFT: Lightweight, FPGA-tailored 3D object detection based on LiDAR datacited by 2
  11. 2026Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Accesscited by 2
  12. 2026TFTrack: A Template-Free Framework for Efficient 3D Point Cloud Trackingcited by 2
  13. 2024LiDAttack: Robust Black-box Attack on LiDAR-based Object Detectioncited by 1
  14. 2025Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Surveycited by 1
  15. 2025Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reportscited by 1
  16. 2024Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detectioncited by 0
  17. 2024RegTrack: Simplicity Beneath Complexity in Robust Multi-Modal 3D Multi-Object Trackingcited by 0
  18. 2025PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilationcited by 0
  19. 2025FALO: Fast and Accurate LiDAR 3D Object Detection on Resource-Constrained Devicescited by 0
  20. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  21. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  22. 2025Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generationcited by 0
  23. 2026Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendationcited by 0
  24. 2026Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detectioncited by 0
  25. 2026Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Drivingcited by 0
  26. 2026SAVTrack: Selective Vote Aggregation for Reliability-Aware Point Cloud Trackingcited by 0
  27. 2026MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Trackingcited by 0