Flow matching-based generative models for MIMO channel estimation

TL;DR

This paper introduces a flow matching-based generative model for MIMO channel estimation that significantly reduces sampling time and improves accuracy compared to diffusion model-based methods.

Contribution

The paper develops a novel flow matching framework for MIMO channel estimation, enabling faster sampling and higher accuracy than existing diffusion model approaches.

Findings

Reduces sampling overhead compared to diffusion models.

Achieves superior channel estimation accuracy.

Demonstrates robustness under various channel conditions.

Abstract

Diffusion model (DM)-based channel estimation, which generates channel samples via a posteriori sampling stepwise with denoising process, has shown potential in high-precision channel state information (CSI) acquisition. However, slow sampling speed is an essential challenge for recent developed DM-based schemes. To alleviate this problem, we propose a novel flow matching (FM)-based generative model for multiple-input multiple-output (MIMO) channel estimation. We first formulate the channel estimation problem within FM framework, where the conditional probability path is constructed from the noisy channel distribution to the true channel distribution. In this case, the path evolves along the straight-line trajectory at a constant speed. Then, guided by this, we derive the velocity field that depends solely on the noise statistics to guide generative models training. Furthermore, during the sampling phase, we utilize the trained velocity field as prior information for channel estimation, which allows for quick and reliable noise channel enhancement via ordinary differential equation (ODE) Euler solver. Finally, numerical results demonstrate that the proposed FM-based channel estimation scheme can significantly reduce the sampling overhead compared to other popular DM-based schemes, such as the score matching (SM)-based scheme. Meanwhile, it achieves superior channel estimation accuracy under different channel conditions.