Research map / Point clouds / Segmentation and detection
Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Point4Bit, a post-training 4-bit quantization method for voxel-based point cloud 3D object detectors.
Problem
Voxel-based 3D detectors are costly in compute and memory for edge deployment, and existing post-training quantization for point cloud detection is limited to INT8 and does not reach 4-bit.
Approach
Post-training 4-bit quantization tailored to voxel-based point cloud 3D detectors, extending PTQ below the INT8 regime that prior point cloud detection PTQ methods were limited to.
Closest papers by meaning
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (ICLR 2024 · similarity 0.89)
- Voxel or Pillar: Exploring Efficient Point Cloud Representation for 3D Object Detection (AAAI 2024 · similarity 0.87)
- X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer (AAAI 2024 · similarity 0.87)
- Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer (NeurIPS 2026 · similarity 0.86)
- Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector (CVPR 2024 · similarity 0.86)
- QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.