Restoration Flow Matching-Based Channel Refinement and Equalization Correction for MIMO Semantic Communications

2026-07-26

AI Summary

This work addresses the degradation of semantic reconstruction quality in MIMO semantic communication caused by imperfect channel state information and equalization mismatch. The authors propose a unified framework based on Restoration Flow Matching (RFM), formulating channel estimation and equalization correction as conditional restoration tasks. A channel RFM module refines coarse channel estimates, while a semantic RFM module corrects residual distortions in the latent space. To balance near-manifold optimization and large-error correction, they introduce an innovative dual-anchor perturbation training strategy. Efficient inference is achieved using a few-step deterministic ODE solver. Experimental results demonstrate that the proposed method significantly improves both channel estimation accuracy and semantic reconstruction quality in MIMO visual semantic transmission tasks, achieving comparable or superior performance with substantially fewer sampling steps than diffusion model baselines.

Abstract

In multiple-input multiple-output (MIMO) semantic communication, imperfect channel state information (CSI) and equalization mismatch can seriously degrade semantic reconstruction quality. To address this issue, we propose a unified restoration flow matching (RFM)-based framework for channel refinement and equalization correction. Specifically, the channel RFM (CRFM) module is developed to refine the coarse channel, thereby improving channel estimation accuracy. Based on the refined channel, the developed semantic RFM (SRFM) module is employed to correct the residual distortions in the post-equalization latent space. The key idea is to formulate the two cascaded inverse problems of channel estimation and equalization as the unified conditional restoration task, in which the learned conditional velocity field guides the perturbed distribution towards the target distribution. To enhance the robustness of these two modules under various distortion conditions, we develop a dual-anchor perturbation training strategy that jointly learns near-manifold refinement and large-error correction, and implement inference through a few-step deterministic ordinary differential equation (ODE) solver. Extensive experiments on MIMO channels and visual semantic transmission tasks demonstrate that the proposed scheme improves key metrics for channel estimation and semantic reconstruction quality. Moreover, compared with representative diffusion-based generative baselines, the proposed method requires fewer sampling steps.

Problem

• MIMO semantic communications
• imperfect channel state information
• equalization mismatch
• semantic reconstruction quality

Innovation

• Restoration Flow Matching
• Channel Refinement
• Equalization Correction
• Semantic Communications
• MIMO