English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Point cloud analytics has become a critical workload for embedded and mobileplatforms across various applications. Farthest point sampling (FPS) is afundamental and widely used kernel in point cloud processing. However, theheavy external memory access makes FPS a performance bottleneck for real-timepoint cloud processing. Although bucket-based farthest point sampling cansignificantly reduce unnecessary memory accesses during the point samplingstage, the KD-tree construction stage becomes the predominant contributor toexecution time. In this paper, we present FuseFPS, an architecture andalgorithm co-design for bucket-based farthest point sampling. We first proposea hardware-friendly sampling-driven KD-tree construction algorithm. Thealgorithm fuses the KD-tree construction stage into the point sampling stage,further reducing memory accesses. Then, we design an efficient accelerator forbucket-based point sampling. The accelerator can offload the entirebucket-based FPS kernel at a low hardware cost. Finally, we evaluate ourapproach on various point cloud datasets. The detailed experiments show thatcompared to the state-of-the-art accelerator QuickFPS, FuseFPS achieves about4.3$\times$ and about 6.1$\times$ improvements on speed and power efficiency,respectively.

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