mlsanityData to 14 Oct 2026

PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds

arXiv 2305.04925 ↗First posted 8 May 2023cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

In order to deal with the sparse and unstructured raw point clouds, LiDAR based 3D object detection research mostly focuses on designing dedicated local point aggregators for fine-grained geometrical modeling. In this paper, we revisit the local point aggregators from the perspective of allocating computational resources. We find that the simplest pillar based models perform surprisingly well considering both accuracy and latency. Additionally, we show that minimal adaptions from the success of 2D object detection, such as enlarging receptive field, significantly boost the performance. Extensive experiments reveal that our pillar based networks with modernized designs in terms of architecture and training render the state-of-the-art performance on the two popular benchmarks: Waymo Open Dataset and nuScenes. Our results challenge the common intuition that the detailed geometry modeling is essential to achieve high performance for 3D object detection.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). Builds on 46 of its 55 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

46 of 55 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  12. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
34 more
  1. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  2. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  3. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  5. 2018Path Aggregation Network for Instance Segmentationcited by 798
  6. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  7. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  8. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  9. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
  10. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  11. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  12. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  13. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  14. 2019Scale-Aware Trident Networks for Object Detectioncited by 159
  15. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
  16. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  17. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  18. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 129
  19. 2021You Only Look One-level Featurecited by 116
  20. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  21. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  22. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  23. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  24. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  25. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  26. 2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
  27. 2021Exploring Simple 3D Multi-Object Tracking for Autonomous Drivingcited by 56
  28. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  29. 2023ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposalscited by 48
  30. 2019Bag of Freebies for Training Object Detection Neural Networkscited by 47
  31. 2021Fast and Accurate Model Scalingcited by 46
  32. 2021Self-Supervised Pillar Motion Learning for Autonomous Drivingcited by 44
  33. 2022Hierarchical Model-Based Imitation Learning for Planning in Autonomous Drivingcited by 44
  34. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 27; 2025: 17; 2026: 5.

54 papers.

Sort:

By area:

  1. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  2. 2023SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radarcited by 49
  3. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  4. 2023DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillationcited by 41
  5. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  6. 2024Unleashing HyDRa: Hybrid Fusion, Depth Consistency and Radar for Unified 3D Perceptioncited by 35
  7. 2023GEDepth: Ground Embedding for Monocular Depth Estimationcited by 26
  8. 2024Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimationcited by 23
  9. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  10. 2024Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehensioncited by 18
  11. 2025Perspective-Invariant 3D Object Detectioncited by 18
  12. 2024DeepInteraction++: Multi-Modality Interaction for Autonomous Drivingcited by 15
38 more
  1. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  2. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
  3. 2023PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detectioncited by 10
  4. 2023Transcendental Idealism of Planner: Evaluating Perception from Planning Perspective for Autonomous Drivingcited by 9
  5. 2025RaGS: Unleashing 3D Gaussian Splatting from 4D Radar and Monocular Cues for 3D Object Detectioncited by 9
  6. 2024SpaRC: Sparse Radar-Camera Fusion for 3D Object Detectioncited by 8
  7. 2024Towards Stable 3D Object Detectioncited by 7
  8. 2024Detect Closer Surfaces that can be Seen: New Modeling and Evaluation in Cross-domain 3D Object Detectioncited by 4
  9. 2024Cross-Modal Self-Supervised Learning with Effective Contrastive Units for LiDAR Point Cloudscited by 4
  10. 2024TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillationcited by 4
  11. 2026SD4R: Sparse-to-Dense Learning for 3D Object Detection with 4D Radarcited by 4
  12. 2024Image-Guided Outdoor LiDAR Perception Quality Assessment for Autonomous Drivingcited by 3
  13. 2024LEROjD: Lidar Extended Radar-Only Object Detectioncited by 3
  14. 2025KAN or MLP? Point Cloud Shows the Way Forwardcited by 3
  15. 2025RadarGaussianDet3D: Gaussian Representation-based Real-time 3D Object Detection with 4D Automotive Radarscited by 3
  16. 2024DCDet: Dynamic Cross-based 3D Object Detectorcited by 2
  17. 2024VADet: Multi-frame LiDAR 3D Object Detection using Variable Aggregationcited by 2
  18. 2025CoreNet: Conflict Resolution Network for Point-Pixel Misalignment and Sub-Task Suppression of 3D LiDAR-Camera Object Detectioncited by 2
  19. 2025PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Modelcited by 2
  20. 2025SFGFusion: Surface Fitting Guided 3D Object Detection with 4D Radar and Camera Fusioncited by 2
  21. 2024Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selectioncited by 1
  22. 2024Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detectioncited by 1
  23. 2024SSF3D: Strict Semi-Supervised 3D Object Detection with Switching Filtercited by 1
  24. 2024FSMDet: Vision-guided feature diffusion for fully sparse 3D detectorcited by 1
  25. 2024Real-time Stereo-based 3D Object Detection for Streaming Perceptioncited by 1
  26. 2025RadarNeXt: Real-Time and Reliable 3D Object Detector Based On 4D mmWave Imaging Radarcited by 1
  27. 2025Pillar-Voxel Fusion Network for 3D Object Detection in Airborne Hyperspectral Point Cloudscited by 1
  28. 2025Physics-Driven Local-Whole Elastic Deformation Modeling for Point Cloud Representation Learningcited by 1
  29. 2025M^3Detection: Multi-Frame Multi-Level Feature Fusion for Multi-Modal 3D Object Detection with Camera and 4D Imaging Radarcited by 1
  30. 2024Power of Cooperative Supervision: Multiple Teachers Framework for Enhanced 3D Semi-Supervised Object Detectioncited by 0
  31. 2024SGCCNet: Single-Stage 3D Object Detector With Saliency-Guided Data Augmentation and Confidence Correction Mechanismcited by 0
  32. 2024Decoupled and Interactive Regression Modeling for High-performance One-stage 3D Object Detectioncited by 0
  33. 2025An Investigation of Beam Density on LiDAR Object Detection Performancecited by 0
  34. 2025VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detectioncited by 0
  35. 2025PointSlice: Accurate and Efficient Slice-Based Representation for 3D Object Detection from Point Cloudscited by 0
  36. 20253DPillars: Pillar-based two-stage 3D object detectioncited by 0
  37. 2025StripDet: Strip Attention-Based Lightweight 3D Object Detection from Point Cloudcited by 0
  38. 2025TransBridge: Boost 3D Object Detection by Scene-Level Completion with Transformer Decodercited by 0

50 most cited of 54 All 54 (JSON)