用雷达-相机协同提升车端感知，抗雨雾且通信高效。
RC-GeoCP: Geometric Consensus for Radar-Camera Collaborative Perception
- 以雷达为几何锚点，统一多车感知坐标系。
- 融合雷达可靠性先验，提升跨车信息对齐精度。
- 适合低算力、恶劣天气下的车联网感知系统。
协同感知（CP）通过多智能体信息共享提升场景理解，但激光雷达系统成本高且易受恶劣天气影响。摄像头与4D雷达组合提供可行替代方案，但其协同机制在CP中仍研究不足。本文提出RC-GeoCP，将雷达从本地辅助信号转变为跨车协作的核心几何锚点，实现低成本、抗恶劣天气、几何稳定的感知。针对深度模糊与空间分散导致的错位问题，提出自车归一化的几何共识机制：复用雷达推导的可靠性先验，用于定位本地BEV特征、选择互补信息并加权接收证据。具体地，几何结构校正（GSR）将视觉语义与雷达生成的几何对齐，生成空间一致的表示；不确定性感知通信（UAC）作为信息过滤器，继承经校正的特征，利用跨车分歧引导选择性通信，聚焦关键区域；最终，共识驱动组装器（CDA）基于自车归一化几何锚点聚合多车信息，形成空间连贯表征。在V2X-Radar和V2X-R数据集上建立统一雷达-相机协同感知评估协议，验证了显著的精度-通信权衡性能。代码即将开源。
原文摘要 · Abstract (English)
Collaborative perception (CP) improves scene understanding through multi-agent information sharing, yet LiDAR-centric systems remain costly and vulnerable in adverse weather. Camera--4D radar offers a practical alternative, but their synergy is still underexplored in CP. We introduce RC-GeoCP, which promotes low-cost, weather-resilient, and geometrically stable radar from an ego-level auxiliary cue to a cross-agent collaboration anchor. To resolve misalignment caused by depth ambiguity and spatial dispersion across agents, RC-GeoCP establishes an ego-normalized geometric consensus: the same radar-derived reliability prior is reused to ground local BEV features, select complementary messages, and weight received evidence. Specifically, Geometric Structure Rectification (GSR) aligns visual semantics with geometry derived from radar to generate spatially grounded, geometry-consistent representations. Uncertainty-Aware Communication (UAC) then serves as an information filter that inherits rectified features from GSR, leveraging inter agent disagreement to steer selective communication toward the most informative regions. Finally, the Consensus-Driven Assembler (CDA) aggregates multi-agent information via ego-normalized geometric anchors to form a spatially coherent representation. We establish a unified radar-camera CP evaluation protocol on V2X-Radar and V2X-R, demonstrating a strong accuracy--communication trade-off. Code will be released soon.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。