GRAM-DIFF: Gram Matrix Guided Diffusion for MIMO Channel Estimation

2026-02-16

AI Summary

This work addresses the underutilization of second-order structural information in received data symbols for semi-blind MIMO channel estimation by proposing a novel approach that integrates angular-domain diffusion priors. The method explicitly incorporates the channel Gram matrix as a subspace constraint during the reverse diffusion process and combines it with pilot-aided likelihood guidance to jointly exploit channel structure and observed data, thereby enhancing estimation accuracy. Key innovations include the first-time embedding of the Gram matrix into a diffusion model, the design of an SNR-matched initialization scheme, and an adaptive guidance scaling mechanism. Evaluated under 3GPP and QuaDRiGa channel models, the proposed method significantly outperforms existing deterministic diffusion-based approaches, achieving a 4–6 dB SNR gain at NMSE = 0.1 and demonstrating robust performance even under limited coherence time conditions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Structured Learning
• Intelligent Robots: State Estimation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

We propose GRAM-DIFF, a Gram-matrix-guided diffusion framework for semi-blind multiple input multiple output (MIMO) channel estimation. Recent diffusion-based estimators leverage learned generative priors to improve pilot-based channel estimation; but they do not exploit second-order structural information estimated from data symbols. In practical systems, the channel Gram matrix can be estimated from received symbols and it provides realization-level information about channel subspace structure. The proposed method integrates a pre-trained angular-domain diffusion prior with two complementary guidance mechanisms: a novel Gram-matrix guidance term that enforces second-order consistency during the reverse diffusion process, and likelihood guidance from pilot observations. Signal-to-noise ratio (SNR)-matched initialization and adaptive guidance scaling ensure stability and low inference latency. Simulations on 3GPP and QuaDRiGa channel models demonstrate consistent normalized mean-squared error (NMSE) improvements over deterministic diffusion baselines, achieving 4 to 6 dB SNR gains at an NMSE of 0.1 over the baseline in Fest et al. (2024). The framework exhibits graceful degradation under coherence-time constraints, smoothly reverting to likelihood-guided diffusion when data-based Gram estimates become unreliable.

Problem

• MIMO channel estimation
• Gram matrix
• diffusion models
• semi-blind estimation
• second-order statistics

Innovation

• Gram matrix guidance
• diffusion model
• MIMO channel estimation
• semi-blind estimation
• second-order statistics