PQuant: Point Cloud Neural Network Acceleration via a Versatile Quantization Framework
Point Cloud Neural Network (PCNN) plays an essential role in various 3D applications, with some of them even being time-sensitive and safety-critical. However, the large scale of unordered points with lengthy features results in heavy computational workloads, making them far from real-time processing. To address this challenge, we propose PQuant, a Morton-code-based fine-grained quantization for accelerating both point-based and voxel-based networks. Specifically, we utilize Morton-code to capture the inherent point similarity and the voxel distribution. Considering the similarity among near points’ features, we decompose features into base and offsets, where the offsets typically exhibit a narrow dynamic range and can thus be quantized using low precision. For the voxel-based networks, spatial location indicated by Morton-codes allows PQuant to apply high precision representation to distant voxels, which are generally sparser and more sensitive to quantization. From the hardware aspect, PQuant integrates a reconfigurable mixed-precision systolic array designed to handle both dense and sparse mixed-precision convolutions in PCNNs. Extensive experiments demonstrate that PQuant achieves 3.7 × and 3.5 × speedup and 5.2 × and 6.0 × energy savings over state-of-the-art PCNN accelerator PointAcc for the point-based and voxel-based networks, respectively.
Authors
- Haibing Guan (ORCID: https://orcid.org/0000-0002-4714-7400)
- Xiaoyao Liang (ORCID: https://orcid.org/0000-0002-2790-5884)
- Zhuoran Song (ORCID: https://orcid.org/0000-0002-6494-4786)
- Jian Weng (ORCID: https://orcid.org/0000-0002-7933-9941)
- X.J. Liu (ORCID: https://orcid.org/0009-0005-1017-5458)
- Hangcheng Dong
- Zhaoxiang Wang (ORCID: https://orcid.org/0009-0001-7588-4336)
- Zhihui Fu (ORCID: https://orcid.org/0000-0002-1488-0569)
- Jun Wang (ORCID: https://orcid.org/0000-0002-3931-9014)
Institutions
- Shanghai Jiao Tong University (CN)
- King Abdullah University of Science and Technology (SA)
Publication Details
- Journal
- ACM Transactions on Architecture and Code Optimization
- Published
- 2026-11-14
- DOI
- https://doi.org/10.1145/3860528
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00