DiffPace: Diffusion-based Plug-and-play Augmented Channel Estimation in mmWave and Terahertz Ultra-Massive MIMO Systems

TL;DR

This work addresses accurate channel estimation in mmWave/THz UM-MIMO with hybrid beamforming under cross-field near-field and far-field propagation. It proposes DiffPace, a diffusion-model plug-and-play CE framework trained on the HPSM to learn realistic channel distributions and solve CE via an ODE-based sampler. DiffPace delivers competitive NMSE at moderate $SNR$ and reduces inference steps by more than 90% compared with stochastic diffusion, while maintaining computational efficiency. Experiments on 60 GHz and 0.3 THz channels show strong cross-environment generalization and robustness to hardware impairments. The approach provides a scalable, physics-informed prior for real-time CE in next-generation wireless systems.

Abstract

Millimeter-wave (mmWave) and Terahertz (THz)-band communications hold great promise in meeting the growing data-rate demands of next-generation wireless networks, offering abundant bandwidth. To mitigate the severe path loss inherent to these high frequencies and reduce hardware costs, ultra-massive multiple-input multiple-output (UM-MIMO) systems with hybrid beamforming architectures can deliver substantial beamforming gains and enhanced spectral efficiency. However, accurate channel estimation (CE) in mmWave and THz UM-MIMO systems is challenging due to high channel dimensionality and compressed observations from a limited number of RF chains, while the hybrid near- and far-field radiation patterns, arising from large array apertures and high carrier frequencies, further complicate CE. Conventional compressive sensing based frameworks rely on predefined sparsifying matrices, which cannot faithfully capture the hybrid near-field and far-field channel structures, leading to degraded estimation performance. This paper introduces DiffPace, a diffusion-based plug-and-play method for channel estimation. DiffPace uses a diffusion model (DM) to capture the channel distribution based on the hybrid spherical and planar-wave (HPSM) model. By applying the plug-and-play approach, it leverages the DM as prior knowledge, improving CE accuracy. Moreover, DM performs inference by solving an ordinary differential equation, minimizing the number of required inference steps compared with stochastic sampling method. Experimental results show that DiffPace achieves competitive CE performance, attaining -15 dB normalized mean square error (NMSE) at a signal-to-noise ratio (SNR) of 10 dB, with 90\% fewer inference steps compared to state-of-the-art schemes, simultaneously providing high estimation precision and enhanced computational efficiency.

Figures (10)

• Figure 1: MmWave and THz UM-MIMO systems with hybrid analog-digital precoding and combining.
• Figure 2: Frame structure for the training process of CE.
• Figure 3: Framework of diffusion-based plug-and-play augmented CE method.
• Figure 4: Network structure of the diffusion denoiser.
• Figure 5: 60 GHz and 0.3 THz channel propagation environment for Raymobtime dataset and Quadriga simulator.