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。AI 中文总结
提出3D点泼溅（3DPS），首个可微雷达点渲染器，基于雷达方程推导，实现物理忠实、复数值和多视点合成，在ColoRadar数据集上性能优于光学NVS基线1.7-5.2倍。
AI 中文摘要
解决毫米波（mmWave）雷达的新视角合成（NVS）问题需要一个物理上忠实、复数值且支持多视点处理的渲染器。此前没有任何方法能同时实现这三个特性。可微蒙特卡洛（MC）光线追踪器直接实现了雷达前向模型，具有显式材料建模和复数输出，但无法扩展到NVS所需的多视角优化。光学NVS移植的NeRF、哈希网格和3D高斯方法训练速度快，但丢弃了相位信息，并用不透明的学习特征替代了显式材料建模，仅限于功率仅距离-方位角（RA）幅度。我们提出了3D点泼溅（3DPS），这是首个用于雷达的可微点渲染器，直接从雷达方程的标准立体角形式推导而来。每个定向3D点携带一个ITU-R P.2040材料模型，以闭式形式评估，并通过预计算的点扩散函数（PSF）将产生的复数相量泼溅到距离单元中。复数输出使渲染器与产品无关。相同的优化场景通过标准快速傅里叶变换（FFT）流程，无需为每种格式重新训练，即可生成模数转换器（ADC）、复数距离剖面（CRP）和RA输出。在六个室外ColoRadar场景上，3DPS在保留的RA图像上达到0.587的平均皮尔逊相关系数。这是三个光学NVS基线（RadarSplat、Radar Fields、DART）的1.7倍到5.2倍。在单个RTX 4090上，每个场景的训练时间约为3分钟。
英文摘要
Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and complex outputs, but do not scale to the multi-view optimization NVS demands. Optical-NVS ports of NeRF, hash grids, and 3D Gaussians train fast but discard phase and replace explicit material modeling with opaque learned features, restricting them to power-only range-azimuth (RA) magnitudes. We propose 3D Point Splatting (3DPS), the first differentiable point renderer for radar, derived directly from the standard solid-angle form of the radar equation. Each oriented 3D point carries an ITU-R P.2040 material model, evaluated in closed form, with the resulting complex phasor splatted into range bins through a precomputed point spread function (PSF). The complex-valued output makes the renderer product-agnostic. The same optimized scene yields analog-to-digital converter (ADC), complex range profile (CRP), and RA outputs through standard fast Fourier transform (FFT) pipelines without retraining for each format. On six outdoor ColoRadar scenes, 3DPS reaches 0.587 mean Pearson correlation on held-out RA images. This is between 1.7x and 5.2x the three optical-NVS baselines (RadarSplat, Radar Fields, DART). Training takes approximately 3 minutes per scene on a single RTX 4090.
CommentsUnder Review
