This paper proposes a deep learning-based channel estimation method for multi-cell interference-limited massive MIMO systems, in which base stations equipped with a large number of antennas serve multiple single-antenna users. The proposed estimator employs a specially designed deep neural network (DNN) based on the deep image prior (DIP) network to first denoise the received signal, followed by conventional least-squares (LS) estimation. We analytically prove that our LS-type deep channel estimator can approach minimum mean square error (MMSE) estimator performance for high-dimensional signals, while avoiding complex channel inversions and knowledge of the channel covariance matrix. This analytical result, while asymptotic, is observed in simulations to be operational for just 64 antennas and 64 subcarriers per OFDM symbol. The proposed method also does not require any training and utilizes several orders of magnitude fewer parameters than conventional DNNs. The proposed deep channel estimator is also robust to pilot contamination and can even completely eliminate it under certain conditions.

中文翻译：

---

使用未经训练的深度神经网络进行大规模 MIMO 信道估计

本文提出了一种基于深度学习的信道估计方法，用于多小区干扰受限的大规模 MIMO 系统，其中配备大量天线的基站为多个单天线用户提供服务。所提出的估计器采用基于深度图像先验 (DIP) 网络的专门设计的深度神经网络 (DNN)，首先对接收信号进行去噪，然后进行传统的最小二乘 (LS) 估计。我们通过分析证明，我们的 LS 型深信道估计器可以接近高维信号的最小均方误差 (MMSE) 估计器性能，同时避免复杂的信道反演和信道协方差矩阵的知识。该分析结果虽然是渐近的，但在模拟中观察到，每个 OFDM 符号仅适用于 64 个天线和 64 个子载波。所提出的方法也不需要任何训练，并且使用的参数比传统 DNN 少几个数量级。所提出的深通道估计器对导频污染也具有鲁棒性，甚至可以在某些条件下完全消除它。