ParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point Clouds. Abstract: As Light Detection And Ranging (LiDAR) increasingly becomes an essential component in robotic navigation and autonomous driving, the processing of high throughput 3D point clouds in real time is widely required.
Mar 24, 2023
This work proposes a highly parallel architecture, namely ParallelNN, for highly efficient kNN search processing of high throughput point clouds.
1 We develop ParallelNN, a highly parallel octree-based. kNN search accelerator for 3D point clouds, which can achieve millisecond-level real-time performance ...
Request PDF | On Feb 1, 2023, Faquan Chen and others published ParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point Clouds ...
This work investigates the architecture design for k-Nearest Neighbor (kNN) search, an important processing kernel for 3D point clouds, and demonstrates the ...
Parallelnn: A parallel octree-based nearest neighbor search accelerator for 3d point clouds ... A configurable and real-time multi-frequency 3D image signal ...
ParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point Clouds pp. 403-414. High Performance and Power Efficient Accelerator ...
Nov 7, 2024 · In this work, we propose CAMPER, a CAM-centered accelerator, aiming to explore the potential of CAM for point cloud range search.
ParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point Clouds · Conference Paper. February 2023. ·. 43 Reads. ·. 11 Citations.
IEEE International Symposium on High-Performance Computer ...
researchr.org › publication › hpca-2023
ParallelNN: A Parallel Octree-based Nearest Neighbor Search Accelerator for 3D Point CloudsFaquan Chen, Rendong Ying, Jianwei Xue, Fei Wen, Peilin Liu. 403 ...