Saved in:
Bibliographic Details
Main Authors: Ma, Ke, Wang, Feng, Lei, Lihui, Tan, Shu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.21484
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911629922271232
author Ma, Ke
Wang, Feng
Lei, Lihui
Tan, Shu
author_facet Ma, Ke
Wang, Feng
Lei, Lihui
Tan, Shu
contents Deep learning-based channel estimation has been recognized as a promising technique for sixth-generation wireless systems. However, most existing approaches rely solely on least-squares estimates obtained from demodulation reference signals, which fail to explicitly exploit channel time-frequency correlation parameters. Inspired by the independent channel parameter estimation enabled by semi-static reference signals in modern wireless systems, this letter presents a parameter-aware deep learning-based channel estimation framework termed HyperCEUNet. Specifically, the proposed hypernetwork generates an adaptive front-end convolutional layer based on estimated channel parameters, serving as a pre-filtering stage before the UNet-based estimator. In addition, the Wiener-filtered channel estimates are adopted to provide a correlation-aware initialization for data resources. Simulation results demonstrate that our proposed HyperCEUNet effectively improves channel estimation accuracy compared with its conventional counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21484
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HyperCEUNet: Parameter-Aware Hypernetwork-Driven UNet for Channel Estimation
Ma, Ke
Wang, Feng
Lei, Lihui
Tan, Shu
Signal Processing
Deep learning-based channel estimation has been recognized as a promising technique for sixth-generation wireless systems. However, most existing approaches rely solely on least-squares estimates obtained from demodulation reference signals, which fail to explicitly exploit channel time-frequency correlation parameters. Inspired by the independent channel parameter estimation enabled by semi-static reference signals in modern wireless systems, this letter presents a parameter-aware deep learning-based channel estimation framework termed HyperCEUNet. Specifically, the proposed hypernetwork generates an adaptive front-end convolutional layer based on estimated channel parameters, serving as a pre-filtering stage before the UNet-based estimator. In addition, the Wiener-filtered channel estimates are adopted to provide a correlation-aware initialization for data resources. Simulation results demonstrate that our proposed HyperCEUNet effectively improves channel estimation accuracy compared with its conventional counterparts.
title HyperCEUNet: Parameter-Aware Hypernetwork-Driven UNet for Channel Estimation
topic Signal Processing
url https://arxiv.org/abs/2604.21484