PQuant: Point Cloud Neural Network Acceleration via a Versatile Quantization Framework
ACM Transactions on Architecture and Code Optimization · 14.11.2026
DOI: 10.1145/3860528 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 14.11.2026. Verfasst von Zhuoran Song und 8 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Song, Z., Dong, H., Liu, X., Fu, Z., Wang, J., Wang, Z., Weng, J., Liang, X., & Guan, H. (2026). PQuant: Point Cloud Neural Network Acceleration via a Versatile Quantization Framework. ACM Transactions on Architecture and Code Optimization. https://doi.org/10.1145/3860528
Vancouver
Song Z, Dong H, Liu X, Fu Z, Wang J, Wang Z, et al. PQuant: Point Cloud Neural Network Acceleration via a Versatile Quantization Framework. ACM Transactions on Architecture and Code Optimization. 2026. doi:10.1145/3860528
BibTeX
@article{Song2026,
author = {Song, Zhuoran and Dong, Hangcheng and Liu, Xueyuan and Fu, Zhihui and Wang, Jun and Wang, Zhaoxiang and Weng, Jian and Liang, Xiaoyao and Guan, Haibing},
title = {PQuant: Point Cloud Neural Network Acceleration via a Versatile Quantization Framework},
journal = {ACM Transactions on Architecture and Code Optimization},
year = {2026},
doi = {10.1145/3860528}
}
EUVIMED