发表机构
Technion; Cornell Tech; NVIDIA（以色列理工学院; 康奈尔科技校区; 英伟达）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DyRAD通过静态背景和动态点反射器建模动态驾驶场景，利用解析点扩散函数渲染完整RAD张量，实现多普勒监督和零样本传感器迁移，显著提升检测恢复率。
AI 中文摘要
从记录的传感器数据重建动态驾驶场景，通过合成超出原始轨迹的观测，支持自动驾驶系统的闭环评估。与相机和激光雷达不同，雷达通过多普勒效应直接测量径向速度。然而，现有的雷达新视角合成未能利用这一能力：处理动态场景的方法仅重建距离-方位张量，而渲染多普勒的方法则假设静态场景。此外，由于雷达处理将每次反射扩散到多个单元，现有表示将此扩散吸收到场景几何中，导致视角移动时渲染不正确。我们提出DyRAD，使用静态背景反射器和运动跟踪的动态点反射器建模动态驾驶场景，以渲染完整的距离-方位-多普勒（RAD）张量。反射器速度从目标跟踪中导出并投影到视线方向，使多普勒既成为渲染输出，又成为这些跟踪的监督信号。关键的是，我们通过从雷达信号处理链推导的固定解析点扩散函数（PSF）渲染反射器，防止传感器引起的扩散被嵌入场景表示中。除了改进场景重建，这种分离还实现了零样本传感器配置迁移，允许同一重建场景在不同雷达规格下渲染而无需重新拟合。我们在RADIal、Boreas和一个合成基准上评估DyRAD，涵盖沿路径姿态和先前工作未测试的偏移视角。在RADIal上，DyRAD在90.7%的参考检测对象中恢复雷达检测，而最强基线仅为26.9%。
英文摘要
Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observations beyond the original trajectory. Unlike cameras and LiDAR, radar measures radial velocity directly through Doppler. Yet existing radar novel-view synthesis fails to exploit this capability: methods addressing dynamic scenes reconstruct only range-azimuth tensors, while methods that render Doppler assume static scenes. Moreover, because radar processing spreads each reflection across multiple bins, existing representations absorb this spread into scene geometry, causing it to render incorrectly when the viewpoint moves. We present DyRAD, which models dynamic driving scenes using static background reflectors and motion-tracked dynamic point reflectors to render complete range-azimuth-Doppler (RAD) tensors. Reflector velocities are derived from object tracks and projected onto the line of sight, making Doppler both a rendered output and supervision for those tracks. Crucially, we render reflectors through a fixed analytic point-spread function (PSF) derived from the radar's signal-processing chain, preventing sensor-induced spread from being baked into the scene representation. Beyond improving scene reconstruction, this separation also enables zero-shot sensor-configuration transfer, allowing the same reconstructed scene to be rendered under different radar specifications without refitting. We evaluate DyRAD on RADIal, Boreas, and a synthetic benchmark across both on-path poses and displaced viewpoints untested by prior work. On RADIal, DyRAD recovers radar detections in 90.7% of reference-detected objects, compared with 26.9% for the strongest baseline.
CommentsProject page: https://dyrad-nvs.github.io/. Code: https://github.com/Dyrad-NVS/DyRAD
