R4Det：面向高性能3D目标检测的4D雷达-相机融合
R4Det: 4D Radar-Camera Fusion for High-Performance 3D Object Detection
面向自动驾驶的多模态3D检测，其全景深度融合（绝对/相对深度互增强）与不依赖自车位姿的可变形门控时序融合模块，可直接迁移到LiDAR-相机或纯视觉BEV时序检测中，解决位姿缺失下的时序退化问题。
原文依据 a Deformable Gated Temporal Fusion module that does not rely on the ego vehicle's pose
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论4D雷达-相机感知配置在自动驾驶中的重要性日益提升。然而，现有融合4D雷达与相机数据的3D目标检测方法面临若干挑战。首先，其绝对深度估计模块的鲁棒性与精度不足，导致3D定位不准确。其次，当自车位姿缺失或不准确时，其时序融合模块的性能会显著下降甚至失效。第三，对于某些小目标，稀疏的雷达点云可能完全无法从其表面反射，此时检测必须仅依赖视觉单模态先验。为解决上述局限，我们提出R4Det，通过全景深度融合模块提升深度估计质量，使绝对深度与相对深度相互增强。在时序融合方面，我们设计了不依赖自车位姿的可变形门控时序融合模块。此外，我们构建了实例引导的动态细化模块，从2D实例引导中提取语义原型。实验表明，R4Det在TJ4DRadSet与VoD数据集上取得了最优的3D目标检测结果。
英文原文摘要 1213 字符
4D radar-camera sensing configuration has gained increasing importance in autonomous driving. However, existing 3D object detection methods that fuse 4D Radar and camera data confront several challenges. First, their absolute depth estimation module is not robust and accurate enough, leading to inaccurate 3D localization. Second, the performance of their temporal fusion module will degrade dramatically or even fail when the ego vehicle's pose is missing or inaccurate. Third, for some small objects, the sparse radar point clouds may completely fail to reflect from their surfaces. In such cases, detection must rely solely on visual unimodal priors. To address these limitations, we propose R4Det, which enhances depth estimation quality via the Panoramic Depth Fusion module, enabling mutual reinforcement between absolute and relative depth. For temporal fusion, we design a Deformable Gated Temporal Fusion module that does not rely on the ego vehicle's pose. In addition, we built an Instance-Guided Dynamic Refinement module that extracts semantic prototypes from 2D instance guidance. Experiments show that R4Det achieves state-of-the-art 3D object detection results on the TJ4DRadSet and VoD datasets.