# FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching

arXiv: https://arxiv.org/abs/2604.17720 · HTML: https://mlsanity.com/paper/2604.17720/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning](https://mlsanity.com/paper/2402.02500/) (2024)
- [PointAcc: Efficient Point Cloud Accelerator](https://mlsanity.com/paper/2110.07600/) (2021)
- [PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning](https://mlsanity.com/paper/2405.15214/) (2024)
- [Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation](https://mlsanity.com/paper/2008.06967/) (2020)
- [Crescent: Taming Memory Irregularities for Accelerating Deep Point Cloud Analytics](https://mlsanity.com/paper/2204.10707/) (2022)
- [L-PCN: A Point Cloud Accelerator Exploiting Spatial Locality through Octree-based Islandization](https://mlsanity.com/paper/2604.10716/) (2026)

## Abstract (arXiv)

Point-based Neural Networks (PNNs) have become a key approach for point cloud processing. However, a core operation in these models, Farthest Point Sampling (FPS), often introduces significant inference latency, especially for large-scale processing. Despite existing CUDA- and hardware-level optimizations, FPS remains a major bottleneck due to exhaustive computations across multiple network layers in PNNs, which hinders scalability. Through systematic analysis, we identify three substantial redundancies in FPS, including unnecessary full-cloud computations, redundant late-stage iterations, and predictable inter-layer outputs that make later FPS computations avoidable. To address these, we propose textbftextitFlashFPS, a hardware-agnostic, plug-and-play framework for FPS acceleration, composed of textitFPS-Prune and textitFPS-Cache. textitFPS-Prune introduces candidate pruning and iteration pruning to reduce redundant computations in FPS while preserving sampling quality, and textitFPS-Cache eliminates layer-wise redundancy via cache-and-reuse. Integrated into existing CUDA libraries and state-of-the-art PNN accelerators, textitFlashFPS achieves 5.16× speedup over the standard CUDA baseline on GPU and 2.69× on PNN accelerators, with negligible accuracy loss, enabling efficient and scalable PNN inference. Codes are released at https://github.com/Yuzhe-Fu/FlashFPS.