RPGFusion：4D雷达先验引导的多模态融合用于3D检测
RPGFusion: 4D Radar Prior-Guided Multi-Modal Fusion for 3D Detection
用4D雷达生成的空间置信度与深度先验图来引导图像特征采样，可缓解Lift-Splat-Shoot视角变换带来的BEV特征近密远疏问题；其稀疏到稠密的特征传播与跨模态空间对齐、语义融合模块，可直接迁移到其他稀疏传感器（LiDAR、事件相机）与相机的BEV融合检测中。
原文依据 These priors guide image feature sampling while preventing the uneven BEV feature distribution (near-dense, far-sparse) caused by Lift-Splat-Shoot view transformation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动驾驶中准确的3D目标检测依赖于有效融合多传感器的互补信息。4D毫米波雷达提供稀疏但物理上可靠的测量，其增强传感器融合的潜力尚未被充分利用。本文提出雷达先验引导融合（RPGFusion），一个实用的4D雷达-相机融合框架。我们首先生成编码空间置信度与深度线索的雷达先验图。这些先验引导图像特征采样，同时避免Lift-Splat-Shoot视角变换所导致的鸟瞰图特征分布不均（近处稠密、远处稀疏）问题。为应对点云固有的稀疏性与噪声，我们采用混合鲁棒编码与稀疏到稠密的特征传播。我们进一步引入空间对齐与语义融合模块，以协调模态间的几何与语义差异，从而得到更一致、更具互补性的鸟瞰图表示。在公开的View-of-Delft与TJ4DRadSet上的大量实验表明，RPGFusion优于先前的雷达-相机融合方法，取得SOTA性能。本工作不仅利用4D雷达信号引导图像鸟瞰图查询，还实现了面向3D感知的鲁棒雷达特征编码与稠密化，展现了4D雷达的强大潜力。
英文原文摘要 1336 字符
Accurate 3D object detection in autonomous driving relies on effectively combining complementary information from multiple sensors. 4D millimeter-wave radar provides sparse yet physically reliable measurements, whose potential for enhancing sensor fusion has not been fully utilized. In this work, we propose Radar Prior Guided Fusion(RPGFusion), a practical 4D radar-camera fusion framework. We first generate radar prior maps that encode spatial confidence and depth cues. These priors guide image feature sampling while preventing the uneven BEV feature distribution (near-dense, far-sparse) caused by Lift-Splat-Shoot view transformation. To address the sparsity and noise inherent in point clouds, we adopt a hybrid robust encoding and sparse-to-dense feature propagation. We further introduce spatial alignment and semantic fusion modules to reconcile geometric and semantic differences between modalities, yielding more consistent and complementary BEV representations. Extensive experiments on the public View-of-Delft and TJ4DRadSet show that RPGFusion outperforms prior radar-camera fusion methods, achieving SOTA performance. Our work not only uses 4D radar signals to guide image BEV queries, but also enables robust radar feature encoding and densification for 3D perception, demonstrating the strong potential of 4D radar.