mlsanityData to 7 Oct 2026

Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder

arXiv 2405.18734 ↗First posted 29 May 2024cs.CV cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder, called PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar with the information entropy guidance. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 49 of its 57 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

49 of 57 references.

References · 49

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  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. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  10. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  12. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
37 more
  1. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  2. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  3. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  4. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  5. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  6. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  7. 2021Voxel Transformer for 3D Object Detectioncited by 247
  8. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  9. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  10. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  11. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  12. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  13. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  14. 2019TANet: Robust 3D Object Detection from Point Clouds with Triple Attentioncited by 108
  15. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  16. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  17. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  18. 2019Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspotscited by 84
  19. 2022Fully Sparse 3D Object Detectioncited by 84
  20. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  21. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  22. 2021PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Cloudscited by 59
  23. 2021Object DGCNN: 3D Object Detection using Dynamic Graphscited by 58
  24. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  25. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  26. 2022VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attentioncited by 48
  27. 20213D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloudcited by 45
  28. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  29. 2020BiPointNet: Binary Neural Network for Point Cloudscited by 30
  30. 2024LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detectioncited by 29
  31. 2022Real-time 3D Single Object Tracking with Transformercited by 27
  32. 2020SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloudcited by 16
  33. 2020Reconfigurable Voxels: A New Representation for LiDAR-Based Point Cloudscited by 16
  34. 2021Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimizationcited by 8
  35. 2023QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detectioncited by 8
  36. 2021Accurate and Real-time 3D Pedestrian Detection Using an Efficient Attentive Pillar Networkcited by 4
  37. 2021Improved Pillar with Fine-grained Feature for 3D Object Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 7; 2026: 6.

14 papers.

Sort:

By area:

  1. 2026ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrievalcited by 39
  2. 2026INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrievalcited by 26
  3. 2026HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrievalcited by 24
  4. 2025FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Modelscited by 15
  5. 2026ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalcited by 15
  6. 2025Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classificationcited by 10
  7. 2024A GEN AI Framework for Medical Note Generationcited by 6
  8. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  9. 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Modelscited by 4
  10. 2025FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detectioncited by 2
  11. 2025Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reportscited by 1
  12. 2026BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviationcited by 1
2 more
  1. 2025Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generationcited by 0
  2. 2025FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detectioncited by 0