RLM：一种用于雷达场景理解的视觉-语言模型方法
RLM: A Vision-Language Model Approach for Radar Scene Understanding
AI总结：
本文提出RadarVLM，通过结构化空间语言监督学习统一的场景表示，改进了雷达场景理解中的空间推理能力，实验显示其在生成描述和车辆分割任务中性能显著提升。
摘要：
雷达传感器在恶劣天气、光照和远距离条件下提供可靠的感知，但现有机器学习方法仍碎片化且任务特定。本文提出RadarVLM，通过结构化空间语言监督学习统一的场景级表示。利用CARLA模拟器和现实雷达模型，收集了超过80万对雷达-描述词对。本文贡献包括：（1）一种编码车辆分布的结构化描述框架，采用雷达原生坐标系；（2）空间感知CLIP（SG-CLIP）目标，用连续场景相似性替代二元匹配，实现细粒度空间推理。进一步提出定位感知评估指标，直接评估空间准确性。在生成描述和车辆分割任务中验证，SG-CLIP在CLIP基础上实现50%的相对F1分数提升，并在分割任务中获得21%的AP提升，证明语言接地产生空间结构化表示。
英文摘要：
Radar sensors provide reliable perception across adverse weather, lighting, and long-range conditions, yet existing machine learning approaches remain fragmented and task-specific, with each downstream task employing distinct architectures and training objectives. We present RadarVLM, a vision-language framework that learns unified scene-level representations through structured spatial language supervision. Leveraging the CARLA simulator with a realistic radar model, we collect over 800k radar-caption pairs across 110+ hours of simulated driving in diverse scenarios. We make two key contributions: (1) a structured caption framework encoding vehicle distributions in the radar's native coordinate system, and (2) Spatially-Grounded CLIP (SG-CLIP) objective that replaces binary matching with continuous scene similarity, enabling fine-grained spatial reasoning. We further propose localization-aware evaluation metrics that directly assess spatial accuracy beyond traditional linguistic similarity measures. Validated on generative captioning and vehicle segmentation, SG-CLIP achieves up to 50% relative F1-score improvement over vanilla CLIP and a 21% AP gain on segmentation, demonstrating that language grounding produces spatially structured representations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
