mmIR：用于3D毫米波雷达ADC合成的频率空间逆渲染方法
mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis
浏览论文内容
中文总结 AI 辅助
提出开源可微分的FMCW雷达逆渲染器mmIR，采用LiDAR辅助逆渲染，在ColoRadar数据集上实现高分辨率3D雷达数据合成，相关性能优于Sionna-RT且可跨雷达硬件迁移。
中文摘要 AI 辅助
高分辨率3D雷达数据十分稀缺。商用毫米波传感器采用小型天线阵列，将角分辨率限制在数度，现有数据集仅提供2D距离-方位角图或稀疏点云，而非原始模数转换器（ADC）信号。硬件扩展成本高昂，合成孔径扫描在车队规模下不切实际，而学习型合成方法受其试图解决的数据短缺问题制约。我们提出mmIR，这是一款开源可微分的调频连续波（FMCW）雷达逆渲染器，它将基于物理的正向模型拟合到真实采集数据，并从密集虚拟孔径重新渲染以合成高分辨率3D雷达数据。由于雷达分辨率过低无法直接恢复几何结构，mmIR采用激光雷达（LiDAR）辅助逆渲染：使用LiDAR生成的网格作为几何支架，通过相位相干多输入多输出（MIMO）正向模型的端到端自动微分，优化每个顶点的国际电信联盟（ITU）物理材料、顶点法线和天线方向图，该模型包含多次反射传播、极化和自由空间衍射。在7个室外和6个室内ColoRadar场景中，mmIR在距离-方位角图上的平均皮尔逊相关系数达0.914，而Sionna-RT为0.307；在级联成像雷达上训练的场景可迁移到共址单芯片雷达，无需重新训练，相关系数为0.554；密集虚拟阵列（100×100个元素）生成的单帧3D占用情况已通过LiDAR验证。项目页面：this https URL
英文摘要
High-resolution 3D radar data is scarce. Commodity mmWave sensors use small antenna arrays that limit angular resolution to several degrees, and existing datasets provide only 2D range-azimuth maps or sparse point clouds rather than raw analog-to-digital converter (ADC) signals. Hardware scaling is expensive, synthetic-aperture scanning is impractical at fleet scale, and learned synthesis methods are bottlenecked by the very data shortage they aim to address. We present mmIR, an open-source differentiable frequency-modulated continuous-wave (FMCW) radar inverse renderer that fits a physics-based forward model to real captures and re-renders from dense virtual apertures to synthesize high-resolution 3D radar data. Because radar resolution is too coarse to recover geometry directly, mmIR performs LiDAR-assisted inverse rendering: using LiDAR-derived meshes as a geometric scaffold, mmIR optimizes per-vertex International Telecommunication Union (ITU) physics materials, vertex normals, and antenna beam patterns through end-to-end automatic differentiation of a phase-coherent multiple-input multiple-output (MIMO) forward model with multi-bounce propagation, polarization, and free-space diffraction. On seven outdoor and six indoor ColoRadar scenes, mmIR achieves 0.914 mean Pearson correlation on range-azimuth maps versus 0.307 for Sionna-RT. Scenes trained on a cascaded imaging radar transfer to a co-located single-chip radar without re-training (0.554 correlation), and dense virtual arrays (100x100 elements) produce single-frame 3D occupancy validated against LiDAR. Project page: https://mmwave-inverse-rendering.github.io/
发表机构
- Cornell Tech（康奈尔科技学院）
机构由 AI 辅助整理，请以论文原文为准。
