用扩散模型生成粒子，让状态估计更准更稳。
DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Models
- 用条件扩散模型学习后验采样，替代传统权重调整。
- 在多模态场景中提升82.8%定位准确率，真实数据提升26%。
- 适合复杂动态系统状态估计，尤其擅长多峰分布建模。
本文提出DiffPF，一种基于扩散模型的可微分粒子滤波方法，用于动态系统的状态估计。与传统可微分粒子滤波依赖预定义或低容量提议分布及重要性加权不同，DiffPF通过将扩散模型条件化于预测粒子和当前观测，学习灵活的后验采样器。该方法可在复杂、高维、多模态的滤波分布中实现无权重偏差的精确采样。我们在多种场景下评估了DiffPF，涵盖单峰与高度多模态分布，并测试了模拟与真实任务。结果表明，其性能持续优于现有滤波基线：在高度多模态全局定位基准上，估计精度提升82.8%；在真实世界KITTI视觉里程计任务上，相比最先进的可微分滤波器提升26%。据我们所知，DiffPF是首个将条件扩散模型引入粒子滤波的方法，实现了高质量后验采样，生成更具信息量的粒子，显著提升状态估计效果。
原文摘要 · Abstract (English)
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.
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。