English

FuseFPS: Accelerating Farthest Point Sampling with Fusing KD-tree Construction for Point Clouds

Hardware Architecture 2024-03-28 v1

Abstract

Point cloud analytics has become a critical workload for embedded and mobile platforms across various applications. Farthest point sampling (FPS) is a fundamental and widely used kernel in point cloud processing. However, the heavy external memory access makes FPS a performance bottleneck for real-time point cloud processing. Although bucket-based farthest point sampling can significantly reduce unnecessary memory accesses during the point sampling stage, the KD-tree construction stage becomes the predominant contributor to execution time. In this paper, we present FuseFPS, an architecture and algorithm co-design for bucket-based farthest point sampling. We first propose a hardware-friendly sampling-driven KD-tree construction algorithm. The algorithm fuses the KD-tree construction stage into the point sampling stage, further reducing memory accesses. Then, we design an efficient accelerator for bucket-based point sampling. The accelerator can offload the entire bucket-based FPS kernel at a low hardware cost. Finally, we evaluate our approach on various point cloud datasets. The detailed experiments show that compared to the state-of-the-art accelerator QuickFPS, FuseFPS achieves about 4.3×\times and about 6.1×\times improvements on speed and power efficiency, respectively.

Cite

@article{arxiv.2309.05017,
  title  = {FuseFPS: Accelerating Farthest Point Sampling with Fusing KD-tree Construction for Point Clouds},
  author = {Meng Han and Liang Wang and Limin Xiao and Hao Zhang and Chenhao Zhang and Xilong Xie and Shuai Zheng and Jin Dong},
  journal= {arXiv preprint arXiv:2309.05017},
  year   = {2024}
}

Comments

conference for ASP-DAC 2024

R2 v1 2026-06-28T12:17:20.932Z