AI 中文总结
本文提出RbFT-Net框架，通过图像条件校正模块校正雷达锚点并选择性传播，解决雷达测量的稀疏与干扰问题，在相关数据集上的深度补全性能优于对比方法。
AI 中文摘要
从相机和毫米波雷达获取密集度量深度预测，可为自主系统提供高性价比的传感方案，但雷达测量天生稀疏，易受杂波、多径反射和投影误差影响。聚合多帧雷达可得到更密集的度量线索，却也会引入时间错位和动态目标干扰，直接传播这类不可靠测量值会破坏预测深度图的大片区域。为解决该问题，本文提出RbFT-Net，一种用于多帧4D雷达-相机深度补全的端到端融合前校正框架。RbFT-Net不假设累积雷达回波准确，而是将其视为带噪时间锚点候选，通过图像条件校正模块联合校正它们的图像平面位置和度量深度，同时估计逐点可靠性；校正后的锚点在高层多模态融合前被选择性传播，从而抑制不可靠测量的影响。在ZJU-4DRadarCam及新采集的4D雷达-相机-激光雷达数据集上的实验表明，RbFT-Net始终优于所评估的独立雷达-相机方法，且与使用辅助单目深度模型的即插即用管道具有竞争力；跨平台评估和组件分析进一步验证了所提校正及感知可靠性的传播策略的有效性。
英文摘要
Dense metric depth prediction from cameras and millimeter-wave radar offers a cost-effective sensing solution for autonomous systems. However, radar measurements are inherently sparse and susceptible to clutter, multipath reflections, and projection errors. While aggregating multiple radar frames provides denser metric cues, it also introduces temporal misalignment and dynamic-object interference. Directly propagating such unreliable measurements can therefore corrupt large regions of the predicted depth map. To address this issue, we propose RbFT-Net, an end-to-end rectify-before-fuse framework for multi-frame 4D radar-camera depth completion. Rather than assuming accumulated radar returns to be accurate, RbFT-Net treats them as noisy temporal anchor candidates. An image-conditioned rectification module jointly corrects their image-plane locations and metric depths while estimating pointwise reliability. The rectified anchors are then selectively propagated before high-level multi-modal fusion, suppressing the influence of unreliable measurements. Experiments on ZJU-4DRadarCam and a newly collected 4D radar-camera-LiDAR dataset show that RbFT-Net consistently outperforms the evaluated independent radar-camera methods and remains competitive with plug-in pipelines using auxiliary monocular depth models. Cross-platform evaluation and component analyses further support the effectiveness of the proposed rectification and reliability-aware propagation strategy.
