Robust MIMO Channel Estimation Using Energy-Based Generative Diffusion Models

TL;DR

Massive MIMO channel estimation is hampered by pilot overhead and latency. The paper introduces an energy-based diffusion model (EBM) that explicitly parameterizes the log-prior via an energy function and uses Metropolis-Hastings corrections to perform accurate posterior sampling for channel estimation. Empirical results show significant NMSE improvements over prior diffusion-based methods and traditional estimators, particularly when pilot resources are scarce, while maintaining reasonable computational complexity. This work provides a robust, data-driven prior framework for high-dimensional CSI that is well-suited to practical deployment in next-generation wireless systems.

Abstract

Channel estimation for massive multiple-input multiple-output (MIMO) systems is fundamentally constrained by excessive pilot overhead and high estimation latency. To overcome these obstacles, recent studies have leveraged deep generative networks to capture the prior distribution of wireless channels. In this paper, we propose a novel estimation framework that integrates an energy-based generative diffusion model (DM) with the Metropolis-Hastings (MH) principle. By reparameterizing the diffusion process with an incorporated energy function, the framework explicitly estimates the unnormalized log-prior, while MH corrections refine the sampling trajectory, mitigate deviations, and enhance robustness, ultimately enabling accurate posterior sampling for high-fidelity channel estimation. Numerical results reveal that the proposed approach significantly improves estimation accuracy compared with conventional parameterized DMs and other baseline methods, particularly in cases with limited pilot overhead.

Figures (4)

• Figure 1: Block diagram of the proposed method.
• Figure 2: NMSE performance when $\alpha = 0.6$.
• Figure 3: NMSE performance when $\alpha = 0.8$.
• Figure 4: NMSE versus pilot density with SNR = 15 dB.