paper-with-me

Papers

Differentiable Particle Filters through Conditional Normalizing Flow

2021-07-01 · Xiongjie Chen, Hao Wen, Yunpeng Li

Differentiable particle filters provide a flexible mechanism to adaptively train dynamic and measurement models by learning from observed data. However, most existing differentiable particle filters are within the bootstrap particle filtering framework and fail to incorporate the information from latest observations to construct better proposals. In this paper, we utilize conditional normalizing flows to construct proposal distributions for differentiable particle filters, enriching the distribution families that the proposal distributions can represent. In addition, normalizing flows are incorporated in the construction of the dynamic model, resulting in a more expressive dynamic model. We demonstrate the performance of the proposed conditional normalizing flow-based differentiable particle filters in a visual tracking task.

📄 PDF Abstract BibTeX arXiv:2107.00488

Code (1)

xiongjiechen/normalizing-flows-dpfs pytorch

Tasks

Visual Tracking

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Normalizing Flow-based Differentiable Particle Filters

2024-03-03 · Xiongjie Chen, Yunpeng Li

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear no…

Density EstimationNormalising FlowsState EstimationState Space Models+1

Conditional Measurement Density Estimation in Sequential Monte Carlo via Normalizing Flow

2022-03-16 · Xiongjie Chen, Yunpeng Li

Tuning of measurement models is challenging in real-world applications of sequential Monte Carlo methods. Recent advances in differentiable particle filters have led to various efforts to learn measurement models through…

Density EstimationvalidVisual Tracking

DiffPF: Differentiable Particle Filtering with Generative Sampling via Conditional Diffusion Models

2025-07-21 · Ziyu Wan, Lin Zhao arxiv

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 weightin…

Visual Odometry

An overview of differentiable particle filters for data-adaptive sequential Bayesian inference

2023-02-19 · Xiongjie Chen, Yunpeng Li

By approximating posterior distributions with weighted samples, particle filters (PFs) provide an efficient mechanism for solving non-linear sequential state estimation problems. While the effectiveness of particle filte…

Bayesian InferenceSequential Bayesian InferenceState Estimation

End-To-End Semi-supervised Learning for Differentiable Particle Filters

2020-11-11 · Hao Wen, Xiongjie Chen, Georgios Papagiannis, Conghui Hu 외

Recent advances in incorporating neural networks into particle filters provide the desired flexibility to apply particle filters in large-scale real-world applications. The dynamic and measurement models in this framewor…

State Estimation