发表机构
Korea Advanced Institute of Science and Technology (KAIST); Korea University（韩国科学技术院（KAIST）; 高丽大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对传统4D雷达预处理忽略下游感知需求的问题，提出场景与任务感知预处理器STAR，通过端到端训练生成任务相关点云，在K-Radar上达74.3 AP，超越SOTA 5.6点，并提升多种3D检测器性能。
AI 中文摘要
四维（4D）雷达已成为环境感知的关键传感器，能够提供距离、方位角、仰角和多普勒测量，同时对光照变化和恶劣天气条件保持鲁棒性。然而，传统的雷达预处理方法（如恒虚警率（CFAR）检测）主要基于信号级标准选择测量值，因此在点云生成过程中可能丢弃对下游感知有价值的信息。此外，现有的4D雷达感知流程通常独立优化雷达数据处理和下游感知，导致任务目标无法直接指导预处理阶段。为解决这些局限性，我们提出了一种场景与任务感知雷达（STAR）预处理器，并配以端到端训练框架。STAR预处理器融合场景上下文和下游任务目标，生成与任务相关的雷达点，使雷达表示能够直接针对感知进行优化。在K-Radar基准上，所提方法实现了74.3 AP，比之前的最先进方法高出5.6个AP点。此外，将STAR生成的任务相关点应用于各种现有3D检测器，在大多数评估设置中提高了检测性能，并且与传统预处理生成的点云相比，总体上获得了正的平均增益。
英文摘要
Four-dimensional (4D) Radar has emerged as a key sensor for environmental perception, providing range, azimuth, elevation, and Doppler measurements while remaining robust to illumination changes and adverse weather conditions. However, conventional Radar preprocessing methods, such as constant false alarm rate (CFAR) detection, select measurements primarily based on signal-level criteria and may therefore discard information valuable for downstream perception during point cloud generation. In addition, existing 4D Radar perception pipelines typically optimize Radar data processing and downstream perception independently, preventing task objectives from directly guiding the preprocessing stage. To address these limitations, we propose a Scene- and Task-Aware Radar (STAR) Preprocessor together with an end-to-end training framework. The STAR Preprocessor incorporates scene context and downstream task objectives to generate task-relevant Radar points, enabling the Radar representation to be optimized directly for perception. On the K-Radar benchmark, the proposed method achieves 74.3 AP, outperforming the previous state of the art by 5.6 AP points. Furthermore, applying the task-relevant points generated by STAR to various existing 3D detectors improves detection performance in most evaluation settings and yields an overall positive average gain over point clouds produced by conventional preprocessing.
