paper-with-me

Papers

FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction

2025-07-31 · Donghyun Lee, Dawoon Jeong, Jae W. Lee, Hongil Yoon arxiv

Deep neural networks have revolutionized 3D point cloud processing, yet efficiently handling large and irregular point clouds remains challenging. To tackle this problem, we introduce FastPoint, a novel software-based acceleration technique that leverages the predictable distance trend between sampled points during farthest point sampling. By predicting the distance curve, we can efficiently identify subsequent sample points without exhaustively computing all pairwise distances. Our proposal substantially accelerates farthest point sampling and neighbor search operations while preserving sampling quality and model performance. By integrating FastPoint into state-of-the-art 3D point cloud models, we achieve 2.55x end-to-end speedup on NVIDIA RTX 3090 GPU without sacrificing accuracy.

📄 PDF Abstract BibTeX arXiv:2507.23480

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

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

2026-06-04 · Ziyang Yu, Xiang Li, Qiong Chang, Jun Miyazaki arxiv

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 …

Autonomous DrivingPoint Clouds

Systolic-CNN: An OpenCL-defined Scalable Run-time-flexible FPGA Accelerator Architecture for Accelerating Convolutional Neural Network Inference in Cloud/Edge Computing

2020-12-06 · Akshay Dua, Yixing Li, Fengbo Ren

This paper presents Systolic-CNN, an OpenCL-defined scalable, run-time-flexible FPGA accelerator architecture, optimized for accelerating the inference of various convolutional neural networks (CNNs) in multi-tenancy clo…

Edge-computing

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting

2025-04-11 · Jiaming Xu, Jiayi Pan, Yongkang Zhou, Siming Chen 외

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM i…

GPULanguage ModelingLanguage ModellingLarge Language Model+2

Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling

2023-12-23 · Shujuan Li, Junsheng Zhou, Baorui Ma, Yu-Shen Liu 외

Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into …

point cloud upsampling

Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis

2025-03-15 · CVPR 2025 1 · Hongyu Sun, Qiuhong Ke, Ming Cheng, Yongcai Wang 외

This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online infe…