Diffusion-based Generative Prior for Low-Complexity MIMO Channel Estimation

arXiv:2403.03545v1 Announce Type: cross
Abstract: 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 …

abstract arxiv cnn complexity convolutional neural network cs.lg diffusion diffusion models eess.sp embedding generative generative models information low network neural network noise novel prior signal type work