RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruning

• URL: http://arxiv.org/abs/2606.06255v1
• Date: Thu, 04 Jun 2026 14:57:05 GMT
• Title: RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruning
• Abstract summary: Point clouds are a primary sensory representation for robotic perception.<n>FPS is the most well-known downsampling operator.<n>FPS scales poorly with the million-point-per-second rates of modern 3D sensors.
• Score: 7.454629583409613
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point clouds are a primary sensory representation for robotic perception, underpinning LiDAR-based autonomous driving, simultaneous localization and mapping (SLAM), and navigation. Within these pipelines, Farthest Point Sampling (FPS) is the most well-known downsampling operator, as its uniform coverage preserves the geometric structure on which downstream perception relies. However, the large time complexity of classical FPS scales poorly with the million-point-per-second rates of modern 3D sensors, making it a dominant latency bottleneck that conflicts with the real-time and limited onboard compute budgets of robotic systems. Therefore, we propose RadiusFPS, an FPS acceleration framework based on spherical voxel pruning that preserves the standard FPS update rule under the same initialization and tie-breaking policy. By indexing the point cloud with spherical voxels, RadiusFPS derives a conservative geometric bound that prunes redundant distance computations in each iteration, complemented by a coordinate-wise point-skip test that removes residual updates. We further introduce RadiusFPS-G, a warp-level GPU implementation that fuses voxel selection, pruning, and distance update into memory-coalesced kernels, eliminating costly global-memory round-trips. On indoor (S3DIS, ScanNet) and outdoor LiDAR (SemanticKITTI) benchmarks, RadiusFPS-G attains up to 2.5x speedup over GPU-based FPS and matches or exceeds QuickFPS among the evaluated methods while using roughly half its GPU memory, with comparable segmentation accuracy. When coupled with the learning-based FastPoint sampler, the resulting pipeline achieves the fastest End-to-End inference among all evaluated configurations. These properties make high-quality FPS-style sampling practical for latency- and memory-constrained robotic vision.

Related papers

• FlashFPS: Efficient Farthest Point Sampling for Large-Scale Point Clouds via Pruning and Caching [10.428491193699374]
  Point-based Neural Networks (PNNs) have become a key approach for point cloud processing.<n>Farthest Point Sampling (FPS) often introduces significant latency.<n>FPS remains a major bottleneck due to exhaustive computations across multiple network layers in PNNs.
  arXiv  Detail & Related papers  (2026-04-20T02:03:24Z)
• PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization [26.426290913965456]
  We present PiLoT, a unified framework that tackles UAV-based ego and target geo-localization.<n>We introduce three key contributions: 1) a Dual-Thread Engine that decouples map rendering from core localization thread, ensuring both low latency and drift-free accuracy.<n>This dataset enables the training of a lightweight network that generalizes in a zero-shot manner from simulation to real data.
  arXiv  Detail & Related papers  (2026-03-21T12:08:46Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction [9.409294413882632]
  We introduce FastPoint, a novel software-based acceleration technique for 3D point cloud processing.<n>By predicting the distance curve, we can efficiently identify subsequent sample points without exhaustively computing all pairwise distances.<n>Our proposal substantially accelerates farthest point sampling and neighbor search operations while preserving sampling quality and model performance.
  arXiv  Detail & Related papers  (2025-07-31T12:02:40Z)
• Online Dense Point Tracking with Streaming Memory [54.22820729477756]
  Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video.<n>Recent point tracking algorithms usually depend on sliding windows for indirect information propagation from the first frame to the current one.<n>We present a lightweight and fast model with textbfStreaming memory for dense textbfPOint textbfTracking and online video processing.
  arXiv  Detail & Related papers  (2025-03-09T06:16:49Z)
• NeRF-Det++: Incorporating Semantic Cues and Perspective-aware Depth Supervision for Indoor Multi-View 3D Detection [72.0098999512727]
  NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by utilizing NeRF to enhance representation learning. We present three corresponding solutions, including semantic enhancement, perspective-aware sampling, and ordinal depth supervision. The resulting algorithm, NeRF-Det++, has exhibited appealing performance in the ScanNetV2 and AR KITScenes datasets.
  arXiv  Detail & Related papers  (2024-02-22T11:48:06Z)
• PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer [75.2251801053839]
  We present a novel Point-Voxel Transformer for single-stage 3D detection (PVT-SSD) We propose a Point-Voxel Transformer (PVT) module that obtains long-range contexts in a cheap manner from voxels. The experiments on several autonomous driving benchmarks verify the effectiveness and efficiency of the proposed method.
  arXiv  Detail & Related papers  (2023-05-11T07:37:15Z)
• IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection [0.5249805590164902]
  Our research focuses on tackling low efficiency issue of point-based methods on large-scale point clouds. Existing point-based methods adopt farthest point sampling (FPS) strategy for downsampling, which is computationally expensive in terms of inference time and memory consumption when the number of point cloud increases. We propose a novel Instance-Centroid Faster Point Sampling Module (IC-FPS) which effectively replaces the first Set Abstraction (SA) layer that is extremely tedious.
  arXiv  Detail & Related papers  (2023-03-31T09:31:29Z)
• FastPillars: A Deployment-friendly Pillar-based 3D Detector [63.0697065653061]
  Existing BEV-based (i.e., Bird Eye View) detectors favor sparse convolutions (known as SPConv) to speed up training and inference. FastPillars delivers state-of-the-art accuracy on Open dataset with 1.8X speed up and 3.8 mAPH/L2 improvement over CenterPoint (SPConv-based)
  arXiv  Detail & Related papers  (2023-02-05T12:13:27Z)
• An Adjustable Farthest Point Sampling Method for Approximately-sorted Point Cloud Data [13.037325916265639]
  We propose adjustable FPS (AFPS), parameterized by M, to aggressively reduce the complexity of FPS without compromising on the sampling performance. AFPS method can achieve 22 to 30x speedup over original FPS. We also propose the nearest-point-distance-updating (N) method to limit the number of distance updates to a constant number.
  arXiv  Detail & Related papers  (2022-08-18T12:23:26Z)
• Fully Sparse 3D Object Detection [57.05834683261658]
  We build a fully sparse 3D object detector (FSD) for long-range LiDAR-based object detection. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module. SIR avoids the time-consuming neighbor queries in previous point-based methods by grouping points into instances.
  arXiv  Detail & Related papers  (2022-07-20T17:01:33Z)
• StrObe: Streaming Object Detection from LiDAR Packets [73.27333924964306]
  Rolling shutter LiDARs emitted as a stream of packets, each covering a sector of the 360deg coverage. Modern perception algorithms wait for the full sweep to be built before processing the data, which introduces an additional latency. In this paper we propose StrObe, a novel approach that minimizes latency by ingesting LiDAR packets and emitting a stream of detections without waiting for the full sweep to be built.
  arXiv  Detail & Related papers  (2020-11-12T14:57:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.