Diffusion-based Generative Prior for Low-Complexity MIMO Channel Estimation
This work addresses channel estimation for MIMO communication systems, offering an incremental improvement over existing generative prior methods.
The paper tackles the problem of low-complexity channel estimation in MIMO systems by proposing a diffusion-based generative prior, resulting in better performance than state-of-the-art methods with reduced complexity and memory overhead.
This work proposes a novel channel estimator based on diffusion models (DMs), one of the currently top-rated generative models. Contrary to related works utilizing generative priors, a lightweight convolutional neural network (CNN) with positional embedding of the signal-to-noise ratio (SNR) information is designed by learning the channel distribution in the sparse angular domain. Combined with an estimation strategy that avoids stochastic resampling and truncates reverse diffusion steps that account for lower SNR than the given pilot observation, the resulting DM estimator has both low complexity and memory overhead. Numerical results exhibit better performance than state-of-the-art channel estimators utilizing generative priors.