IEEE

MNAT-Net: Multi-Scale Neighborhood Aggregation Transformer Network for Point Cloud Classification and Segmentation

Abstract: Accurate understanding of 3D objects in complex scenes plays essential roles in the fields of intelligent transportation and autonomous driving technology. Recent deep neural networks have ...
IEEE

PN-Internet: Point-and-Normal Interactive Network for Noisy Point Clouds

Abstract: Point cloud denoising and normal estimation are two fundamental yet dependent problems in digital geometry processing. However, both are often independently researched, leading to ...
IEEE

MMCNet: Multi-Modal Point Cloud Completion Network Based on Self-Projected Views

Abstract: Obtaining defect-free point cloud data is challenging due to performance constraints of acquisition devices and unavoidable occlusion, making point cloud data completion critical. In recent ...
IEEE

MCTNet: Multiscale Cross-Attention-Based Transformer Network for Semantic Segmentation of Large-Scale Point Cloud

Abstract: In this work, we implement a hybrid method to utilize sufficient information by aggregating both fine-grained and globally contextual features for point cloud semantic segmentation with a ...
IEEE

Point to Point Virtual Private Network Scheme Based on 5G Communication Terminal

Abstract: Aiming at the long-distance trans-regional transmission of power data in the new power system, this paper first analyzes the suitability of 5G communication network and power business, then ...
IEEE

BICANet: LiDAR Point Cloud Classification Network Based on Coordinate Attention and Blueprint Separation Involution Neural Network

Abstract: With the advent of the era of Industry 4.0 and the continuous development of point cloud data acquisition technology, point cloud data have been widely used in the unmanned distribution of ...
IEEE

Mask-SL RCNN: Feature-Enhanced 3D Object Detection Network for Point Clouds

Abstract: At present, with the original point cloud as input, most of the object detectors use Pointnet++ to extract features of the point cloud based on the Farthest Point Sampling (FPS). However, ...
IEEE

PointCT: Point Central Transformer Network for Weakly-supervised Point Cloud Semantic Segmentation

Abstract: Although point cloud segmentation has a principal role in 3D understanding, annotating fully large-scale scenes for this task can be costly and time-consuming. To resolve this issue, we ...
IEEE

RID-Net: A Hybrid MLP-Transformer Network for Robust Point Cloud Registration

Abstract: The robustness of correspondence-based point cloud registration relies on transformation invariance and intrinsic distinctiveness of the descriptors computed for registration. However, for ...
IEEE

Empowering Cloud Computing With Network Acceleration: A Survey

Abstract: Modern interactive and data-intensive applications must operate under demanding time constraints, prompting a shift toward the adoption of specialized software and hardware network ...
IEEE

PCGNet: Point Cloud Generation Network for 3D Perception Using Monocular Images and Radar

Abstract: Millimeter-wave (mmWave) radar is widely used in autonomous driving thanks to its robustness under harsh weather conditions. However, compared to LiDAR point clouds, mmWave radar point ...
IEEE

A 38.5TOPS/W Point Cloud Neural Network Processor with Virtual Pillar and Quadtree-based Workload Management for Real-Time Outdoor BEV Detection

Abstract: In recent years, the significance of 3D point cloud processing has witnessed a remarkable upsurge, particularly in emerging application domains such as autonomous vehicles and mixed reality.