{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lidar-ptq-post-training-quantization-for","title":"LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection","arxiv_id":"2401.15865","date":"2024-01-29","proceeding":null,"authors":["Sifan Zhou","Liang Li","Xinyu Zhang","Bo Zhang","Shipeng Bai","Miao Sun","Ziyu Zhao","Xiaobo Lu","Xiangxiang Chu"],"abstract":"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, \\textbf{(1)} a sparsity-based calibration method to determine the initialization of quantization parameters, \\textbf{(2)} a Task-guided Global Positive Loss (TGPL) to reduce the disparity between the final predictions before and after quantization, \\textbf{(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 $3\\times$ inference speedup. Moreover, our LiDAR-PTQ is cost-effective being $30\\times$ faster than the quantization-aware training method. Code will be released at \\url{https://github.com/StiphyJay/LiDAR-PTQ}.","url_abs":"https://arxiv.org/abs/2401.15865v1","url_pdf":"https://arxiv.org/pdf/2401.15865v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lidar-ptq-post-training-quantization-for","repo_url":"https://github.com/stiphyjay/lidar-ptq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.15865","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}