mlsanityData to 7 Oct 2026

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

arXiv 2401.15865 ↗First posted 29 Jan 2024cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Due to highly constrained computing power and memory, deploying 3D lidar-based detectors on edge devices equipped in autonomous vehicles and robots poses a crucial challenge. Being a convenient and straightforward model compression approach, Post-Training Quantization (PTQ) has been widely adopted in 2D vision tasks. However, applying it directly to 3D lidar-based tasks inevitably leads to performance degradation. As a remedy, we propose an effective PTQ method called LiDAR-PTQ, which is particularly curated for 3D lidar detection (both SPConv-based and SPConv-free). Our LiDAR-PTQ features three main components, (1) a sparsity-based calibration method to determine the initialization of quantization parameters, (2) a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, (3) an adaptive rounding-to-nearest operation to minimize the layerwise reconstruction error. Extensive experiments demonstrate that our LiDAR-PTQ can achieve state-of-the-art quantization performance when applied to CenterPoint (both Pillar-based and Voxel-based). To our knowledge, for the very first time in lidar-based 3D detection tasks, the PTQ INT8 model's accuracy is almost the same as the FP32 model while enjoying 3× inference speedup. Moreover, our LiDAR-PTQ is cost-effective being 30× faster than the quantization-aware training method. Code will be released at urlhttps://github.com/StiphyJay/LiDAR-PTQ.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 29 Jan 2024.

Builds on

29 of 38 references.

References · 29

  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. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  4. 2019Learned Step Size Quantizationcited by 604
  5. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  6. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  7. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  8. 2021A White Paper on Neural Network Quantizationcited by 453
  9. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  10. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  11. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  12. 2019Low-bit Quantization of Neural Networks for Efficient Inferencecited by 185
17 more
  1. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  2. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  3. 2022Fully Sparse 3D Object Detectioncited by 84
  4. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  5. 2022NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformerscited by 59
  6. 2020EasyQuant: Post-training Quantization via Scale Optimizationcited by 57
  7. 2022Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Imagescited by 56
  8. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  9. 2019Training Quantized Neural Networks with a Full-precision Auxiliary Modulecited by 35
  10. 2023Super Sparse 3D Object Detectioncited by 32
  11. 2020BiPointNet: Binary Neural Network for Point Cloudscited by 30
  12. 2022Make RepVGG Greater Again: A Quantization-aware Approachcited by 21
  13. 2018Quantization Mimic: Towards Very Tiny CNN for Object Detectioncited by 20
  14. 2022RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantizationcited by 14
  15. 2021Deployment of Deep Neural Networks for Object Detection on Edge AI Devices with Runtime Optimizationcited by 8
  16. 2023QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detectioncited by 8
  17. 2020AQD: Towards Accurate Fully-Quantized Object Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 10; 2026: 12.

29 papers.

Sort:

By area:

  1. 2024MobileVLM V2: Faster and Stronger Baseline for Vision Language Modelcited by 172
  2. 2024Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectivescited by 22
  3. 2024I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Modelscited by 19
  4. 2026ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrievalcited by 15
  5. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  6. 2025QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perceptioncited by 11
  7. 2025Saliency-Aware Quantized Imitation Learning for Efficient Robotic Controlcited by 8
  8. 2024A GEN AI Framework for Medical Note Generationcited by 6
  9. 2024PTQ4RIS: Post-Training Quantization for Referring Image Segmentationcited by 4
  10. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  11. 2026Rethinking LoRA for Privacy-Preserving Federated Learning in Large Modelscited by 4
  12. 2024PillarTrack:Boosting Pillar Representation for Transformer-based 3D Single Object Tracking on Point Cloudscited by 2
17 more
  1. 2025Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarkscited by 2
  2. 2026Vanishing Watermarks: Diffusion-Based Image Editing Undermines Robust Invisible Watermarkingcited by 2
  3. 2026Same Question, Different Answer? Measuring and Mitigating Prompt Privilege for Equitable AI Accesscited by 2
  4. 2025Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reportscited by 1
  5. 2026Editing on the Generative Manifold: A Theoretical and Empirical Study of General Diffusion-Based Image Editing Trade-offscited by 1
  6. 2025UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehiclescited by 0
  7. 2025FADE: Adversarial Concept Erasure in Flow Modelscited by 0
  8. 2025Robust Concept Erasure in Diffusion Models: A Theoretical Perspective on Security and Robustnesscited by 0
  9. 2025Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generationcited by 0
  10. 2025D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Modelscited by 0
  11. 2026RPIQ: Residual-Projected Multi-Collaboration Closed-Loop and Single Instance Quantization for Visually Impaired Assistancecited by 0
  12. 2026Mixed Precision PointPillars for Efficient 3D Object Detection with TensorRTcited by 0
  13. 2026Inlier-Centric Post-Training Quantization for Object Detection Modelscited by 0
  14. 2026When Denoising Becomes Unsigning: Theoretical and Empirical Analysis of Watermark Fragility Under Diffusion-Based Image Editingcited by 0
  15. 2026Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarkingcited by 0
  16. 2026On the Controllability-Fidelity Frontier in Diffusion Editingcited by 0
  17. 2026MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Trackingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PointLAM: Local Attentive Mamba for Efficient Point-based 3D Object Detection
  2. 2025Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences
  3. 2026On the Feasibility and Opportunity of Autoregressive 3D Object Detection
  4. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models
  5. 2025LiDAR Point Cloud Image-based Generation Using Denoising Diffusion Probabilistic Models
  6. 2024DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection
  7. 2026PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds
  8. 2024Fast LiDAR Upsampling using Conditional Diffusion Models