Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection

Jianyu Wang, Yu Wang, Shengjie Zhao, Sifan Zhou

Tongji University· Carnegie Mellon University

Point Cloud Detection Post-training Quantization Model Compression

Abstract

Voxel-based 3D object detectors have achieved remarkable performance in point cloud perception, yet their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Post-training quantization (PTQ) provides a practical means to compress models and accelerate inference; however, existing PTQ methods for point cloud detection are typically limited to INT8 and lack support for lower-bit formats such as INT4, which restricts their deployment potential.

In this paper, we present Point4bit, the first general 4-bit PTQ framework tailored for voxel-based 3D object detectors. To tackle challenges in low-bit quantization, we propose two key techniques:

Foreground-aware Piecewise Activation Quantization (FA-PAQ), which leverages foreground structural cues to improve the quantization of sparse activations; and
Gradient-guided Key Weight Quantization (G-KWQ), which preserves task-critical weights through gradient-based analysis to reduce quantization-induced degradation.

Extensive experiments demonstrate that Point4bit achieves INT4 quantization with minimal accuracy loss with less than 1.5% accuracy drop. Moreover, we validate its generalization ability on point cloud classification and segmentation tasks, demonstrating broad applicability. Our method further advances the bit-width limitation of point cloud quantization to 4 bits, demonstrating strong potential for efficient deployment on resource-constrained edge devices.