发表机构
College of Information Science and Electronic Engineering, Zhejiang University; Zhejiang Key Laboratory of Multimodal Communication Networks and Intelligent Information Processing（浙江大学信息与电子工程学院; 浙江省多模态通信网络与智能信息处理重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无人机三维定位中激光雷达稀疏、模态失衡和特征冗余问题，提出PRI-Net轻量级多模态框架，结合点云溅射、残差注意力融合和信息瓶颈，实现高精度、高效且鲁棒的定位。
AI 中文摘要
由于激光雷达点云几何稀疏、模态融合不平衡以及受限边缘到服务器链路上的冗余特征传输，现有的多模态方法在实现无人机（UAV）精确三维定位方面仍面临挑战。为解决这些局限性，我们提出了PRI-Net，一种高效且轻量级的多模态融合框架，用于无人机定位，该框架集成了点云溅射、残差注意力融合和信息瓶颈技术。具体而言，引入了一种三维点云溅射（3DPCS）策略，将稀疏的激光雷达观测转换为几何一致的密集深度图。随后设计了一个残差注意力融合（RAF）模块，通过使用图像分支进行粗估计和门控融合分支进行细化，来缓解模态偏差。此外，一个多模态信息瓶颈（MIB）模块通过过滤与任务无关的冗余来压缩特征。实验表明，PRI-Net在轻量级架构下实现了高定位精度，同时降低了特征维度，并提高了边缘到服务器无人机感知的效率和鲁棒性。
英文摘要
Accurate 3D localization of unmanned aerial vehicles (UAVs) remains challenging for existing multimodal approaches due to sparse LiDAR geometry, modality-imbalanced fusion, and redundant feature transmission over constrained edge-to-server links. To address these limitations, we propose PRI-Net, an efficient and lightweight multimodal fusion framework for UAV localization that integrates point cloud splatting, residual attention fusion, and an information bottleneck. Specifically, a 3D point cloud splatting (3DPCS) strategy is introduced to transform sparse LiDAR observations into geometrically consistent dense depth maps. A residual attention fusion (RAF) module is then designed to alleviate modal bias by using an image branch for coarse estimation and a gated fusion branch for refinement. In addition, a multimodal information bottleneck (MIB) module compacts features by filtering task-irrelevant redundancy. Experiments show that PRI-Net achieves high localization accuracy with lightweight architectures, while reducing feature dimensionality and improving edge-to-server UAV sensing efficiency and robustness.
CommentsAccepted by IEEE PIMRC 2026
