仅一次流：基于多假设归一化流的校准且实时雷达位姿估计
You Only Flow Once: Calibrated and Real-Time Radar Pose Estimation with Multi-Hypothesis Normalizing Flows
- Friedrich-Alexander-Universität Erlangen-Nürnberg（弗里德里希-亚历山大-埃尔兰根-纽伦堡大学）
- Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
- LMU München（慕尼黑大学）
- Helmholtz Zentrum München（慕尼黑亥姆霍兹中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对雷达位姿估计的歧义问题，提出MH-NFPG方法，结合时空Transformer与归一化流，实现高效实时的校准位姿估计，性能优于扩散模型。
AI中文摘要：
稀疏且含噪的毫米波雷达点云观测通常对应多种可能的人体位姿，使得确定性位姿估计本质上是不适定的。然而现有的雷达方法仍为确定性方法，将这种歧义性坍缩为单一估计。基于扩散的替代方法可以建模多假设分布，但需要对每个分布样本进行代价高昂的序列去噪，且缺乏校准的不确定性。我们提出多假设归一化流位姿生成器（MH-NFPG），其通过条件归一化流建模雷达点云的位姿分布。具体而言，我们将时空Transformer骨干网络与归一化流相结合，该归一化流将拉普拉斯基分布转换为表达性后验分布，通过单次前向传播并行生成。利用这种效率，我们在三个雷达基准（MM-Fi、mmRadPose、mRI）上的校准性能优于基于扩散的替代方法，在两个基准上提高了位姿精度，在第三个基准上与之匹配，同时实现了超过20倍的推理速度以满足应用需求，并将校准误差降低了多达85%。我们发现扩散模型的校准性能会大幅下降，而我们基于流的方法在跨环境设置中也能保持可靠的覆盖度。这些结果表明，归一化流是用于实时、感知不确定性的雷达位姿估计的扩散模型的实用替代方案。我们的代码将公开提供。
英文摘要：
Sparse and noisy millimeter-wave radar point cloud observations often correspond to multiple plausible human poses, making deterministic pose estimation fundamentally ill-posed. Yet existing radar methods remain deterministic, collapsing this ambiguity into a single estimate. Diffusion-based alternatives can model multi-hypothesis distributions but require costly sequential denoising for each distribution sample and lack calibrated uncertainty. We propose Multi-Hypothesis Normalizing Flow Pose Generator (MH-NFPG), which models pose distributions from radar point clouds using a conditional normalizing flow. Specifically, we combine a spatiotemporal transformer backbone with a normalizing flow that transforms a Laplace base distribution into an expressive posterior, generated in parallel through a single forward pass. Leveraging this efficiency, we outperform diffusion-based alternatives in calibration across three radar benchmarks (MM-Fi, mmRadPose, mRI), improve pose accuracy on two, and match it on the third, while achieving over 20x faster inference for applications and reducing calibration error by up to 85%. We find that calibration degrades substantially for diffusion models, whereas our flow-based approach maintains reliable coverage, also in cross-environment settings. These results demonstrate normalizing flows as a practical alternative to diffusion models for real-time, uncertainty-aware radar pose estimation. Our code will be made publicly available.
