This paper proposes DiffPF, a differentiable particle filter that leverages diffusion models for state estimation in dynamic systems. Unlike conventional differentiable particle filters, which require importance weighting and typically rely on predefined or low-capacity proposal distributions. DiffPF learns a flexible posterior sampler by conditioning a diffusion model on predicted particles and the current observation. This enables accurate, equally-weighted sampling from complex, high-dimensional, and multimodal filtering distributions. We evaluate DiffPF across a range of scenarios, including both unimodal and highly multimodal distributions, and test it on simulated as well as real-world tasks, where it consistently outperforms existing filtering baselines. In particular, DiffPF achieves an 82.8% improvement in estimation accuracy on a highly multimodal global localization benchmark, and a 26% improvement on the real-world KITTI visual odometry benchmark, compared to state-of-the-art differentiable filters. To the best of our knowledge, DiffPF is the first method to integrate conditional diffusion models into particle filtering, enabling high-quality posterior sampling that produces more informative particles and significantly improves state estimation.

翻译：本文提出DiffPF，一种利用扩散模型进行动态系统状态估计的可微分粒子滤波方法。与传统的可微分粒子滤波（通常需要重要性加权并依赖预定义或低容量提议分布）不同，DiffPF通过将扩散模型以预测粒子和当前观测为条件，学习一个灵活的后验采样器。这使得我们能够从复杂、高维、多模态的滤波分布中进行精确的等权重采样。我们在包括单模态和高度多模态分布在内的一系列场景中评估DiffPF，并在仿真及真实世界任务上进行测试，其性能始终优于现有滤波基线方法。具体而言，在高度多模态的全局定位基准测试中，DiffPF实现了82.8%的估计精度提升；在真实世界KITTI视觉里程计基准测试中，相较于最先进的可微分滤波器，其性能提升了26%。据我们所知，DiffPF是首个将条件扩散模型集成到粒子滤波中的方法，实现了高质量的后验采样，从而产生信息量更丰富的粒子并显著改进了状态估计。