EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

Deep Generative Channel Estimation for Wideband Beamspace Massive MIMO Systems: A Physics-Informed Pix2pix Approach

Yang Nie, Zhenghuan Ma, Lili Jing

Electronics · 2026-11-20 · 15 (22) · 5423

DOI: 10.3390/electronics15225423 ↗

At a glance

Journal article in Electronics, published online on 2026-11-20. Written by Yang Nie and 2 co-authors. 34 references. The full text is freely available (open access, CC BY 4.0). Funded by: Science and Technology at the Universities of Inner Mongolia Autonomous Region, Jining Normal University.

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Reliable channel state information (CSI) acquisition in wideband beamspace massive multiple-input multiple-output (MIMO) systems is hampered by the beam-squint effect and the structural mismatch of conventional deep learning (DL) estimators. To address these challenges, we propose a physics-informed conditional Wasserstein generative adversarial network with gradient penalty (CWGAN-GP) scheme, termed initial-estimate-enhanced Pix2pix (IE-Pix2pix), which integrates model-driven initialization with structure-preserving adversarial refinement. Specifically, a linear signal preprocessing (LSP) operator generates a physics-informed initial estimate as the conditional input, and a trajectory-aware loss is incorporated to preserve the frequency-dependent sparsity of the beamspace channel. Simulation results show that the proposed scheme attains an NMSE of −23.5 dB at 10 dB SNR, about 2.5 dB lower than the strongest DL baseline, and reaches −31.2 dB at 30 dB, about 2.2 dB lower than the strongest baseline while clearly avoiding the error floor of conventional compressive-sensing estimators. Moreover, the achievable spectral efficiency at 30 dB reaches about 166 bps/Hz, approximately 12 bps/Hz higher than the conditional GAN baseline and 98 bps/Hz higher than OMP.

Funding

  • Science and Technology at the Universities of Inner Mongolia Autonomous Region
  • Jining Normal University

Cite

APA

Nie, Y., Ma, Z., & Jing, L. (2026). Deep Generative Channel Estimation for Wideband Beamspace Massive MIMO Systems: A Physics-Informed Pix2pix Approach. Electronics, 15(22), 5423. https://doi.org/10.3390/electronics15225423

Vancouver

Nie Y, Ma Z, Jing L. Deep Generative Channel Estimation for Wideband Beamspace Massive MIMO Systems: A Physics-Informed Pix2pix Approach. Electronics. 2026;15(22):5423. doi:10.3390/electronics15225423

BibTeX
@article{Nie2026,
  author = {Nie, Yang and Ma, Zhenghuan and Jing, Lili},
  title = {Deep Generative Channel Estimation for Wideband Beamspace Massive MIMO Systems: A Physics-Informed Pix2pix Approach},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {22},
  pages = {5423},
  doi = {10.3390/electronics15225423}
}
Start for free →