SNR-Gated LSTM-Conditioned Diffusion Model for MIMO Channel Estimation

2026-10-06

AI Summary

This study addresses the challenge of jointly balancing estimation accuracy and latency when exploiting structured sparsity and temporal correlation in mobile MIMO channel estimation. To this end, we propose a temporally conditioned diffusion framework that employs an LSTM to encode historical observations for capturing dynamic channel evolution, while performing denoising in the angular domain to achieve high-fidelity reconstruction. The core innovation lies in introducing a learnable SNR-gated shortcut fusion mechanism to balance data fidelity with prior information. Furthermore, DDIM sampling combined with an SNR-adaptive truncation strategy is incorporated to substantially reduce inference latency. Simulation results demonstrate that the proposed method outperforms existing baselines across a wide SNR range while maintaining a distinct low-latency advantage.

Abstract

Accurate and low latency channel estimation is critical for modern MIMO systems, particularly under mobility, where channels exhibit structured sparsity and strong temporal correlation. This paper proposes a time-series conditioned diffusion framework for channel estimation that performs denoising in the angular domain. Starting from least squares (LS) observations, we train a diffusion denoiser whose conditioning information is encoded by a long short-term memory (LSTM) network over a short observation sequence, enabling the model to exploit temporal dynamics beyond per-snapshot estimation. To robustly balance observation fidelity and learned generative priors across a wide signal-to-noise ratio (SNR) range, we introduce a learnable SNR-gated late-fusion shortcut that injects the network input into the final decoding stage through a sigmoid gate with trainable center and scale. To reduce inference latency, we adopt deterministic denoising diffusion implicit model (DDIM) style reverse updates with SNR-adaptive truncation and step allocation, which significantly reduces the number of reverse diffusion steps at high SNR while maintaining strong performance in low SNR regimes. Simulations on time-evolving standardized channel models demonstrate that the proposed method achieves consistent performance gains over existing diffusion-based channel estimation baselines, while retaining low latency through SNR-adaptive inference.

Problem

• MIMO channel estimation
• low latency
• mobility
• structured sparsity
• temporal correlation

Innovation

• Diffusion Model
• MIMO Channel Estimation
• LSTM-Conditioned
• SNR-Gated Late-Fusion
• DDIM Adaptive Inference