用物理模型反演雷达信号，生成高分辨率3D毫米波数据
mmIR: Frequency-Space Inverse Rendering for 3D Millimeter-Wave Radar ADC Synthesis
- 基于物理的逆渲染，结合LiDAR几何与雷达传播模型
- 在7个室外/6个室内场景上相关性达0.914，超基线0.307
- 无需重训练即可迁移至真实单芯片雷达，适合自动驾驶感知研究
高分辨率3D雷达数据稀缺。商用毫米波传感器使用小阵列，角分辨率仅几度，现有数据集仅提供2D距离-方位图或稀疏点云，而非原始模数转换器（ADC）信号。硬件扩容成本高，合成孔径扫描难以规模化，现有学习方法又受限于数据短缺。本文提出mmIR，一个开源可微分频率调制连续波（FMCW）雷达逆渲染框架，通过拟合真实采集数据，从密集虚拟天线阵列重建高分辨率3D雷达数据。由于雷达分辨率不足直接恢复几何，mmIR采用LiDAR辅助逆渲染：以LiDAR获取的网格为几何骨架，端到端优化顶点级国际电信联盟（ITU）物理材质、顶点法向及天线波束模式，基于相位一致的多输入多输出（MIMO）前向模型，包含多路径传播、极化与自由空间衍射。在7个室外和6个室内ColoRadar场景中，mmIR在距离-方位图上的平均皮尔逊相关性达0.914，远超Sionna-RT的0.307。在级联成像雷达上训练的模型可无须重训练迁移至同位置单芯片雷达（相关性0.554），而密集虚拟阵列（100×100单元）生成的单帧3D占用图经LiDAR验证有效。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。