EUVIMEDEUVIMED entdecken
Crossref

Residual Diffusion Models for Variable-Rate Joint Source–Channel Coding of MIMO CSI

Sravan Kumar Ankireddy, Heasung Kim, Joonyoung Cho, Hyeji Kim

IEEE Journal on Selected Areas in Communications · 2026 · 44 · 3620-3633

DOI: 10.1109/jsac.2026.3666741 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2026. Verfasst von Sravan Kumar Ankireddy und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Samsung Research America through the 6G@UT Center within the Wireless Networking and Communications Group (WNCG) at The University of Texas at Austin through A…, Office of Naval Research, NSF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite significant advancements in deep learning-based CSI compression, some key limitations remain unaddressed. Current approaches predominantly treat CSI compression as a source-coding problem, thereby neglecting transmission errors. Conventional separate source and channel coding suffers from the cliff effect, leading to significant deterioration in reconstruction performance under challenging channel conditions. While existing autoencoder-based compression schemes can be readily extended to support joint source-channel coding, they struggle to capture complex channel distributions and exhibit poor scalability with increasing parameter count. To overcome these inherent limitations of autoencoder-based approaches, we propose Residual-Diffusion Joint Source-Channel Coding (RD-JSCC), a novel framework that integrates a lightweight autoencoder with a residual diffusion module to iteratively refine CSI reconstruction. Our flexible decoding strategy balances computational efficiency and performance by dynamically switching between low-complexity autoencoder decoding and sophisticated diffusion-based refinement based on channel conditions. Comprehensive simulations demonstrate that RD-JSCC significantly outperforms existing autoencoder-based approaches in challenging wireless environments. Furthermore, RD-JSCC offers several practical features, including a low-latency 2-step diffusion during inference, support for multiple compression rates with a single model, robustness to fixed-bit quantization, and adaptability to imperfect channel estimation.

Förderung

  • Samsung Research America through the 6G@UT Center within the Wireless Networking and Communications Group (WNCG) at The University of Texas at Austin through A…
  • Office of Naval Research
  • NSF

Zitieren

APA

Ankireddy, S. K., Kim, H., Cho, J., & Kim, H. (2026). Residual Diffusion Models for Variable-Rate Joint Source–Channel Coding of MIMO CSI. IEEE Journal on Selected Areas in Communications, 44, 3620-3633. https://doi.org/10.1109/jsac.2026.3666741

Vancouver

Ankireddy SK, Kim H, Cho J, Kim H. Residual Diffusion Models for Variable-Rate Joint Source–Channel Coding of MIMO CSI. IEEE Journal on Selected Areas in Communications. 2026;44:3620-3633. doi:10.1109/jsac.2026.3666741

BibTeX
@article{Ankireddy2026,
  author = {Ankireddy, Sravan Kumar and Kim, Heasung and Cho, Joonyoung and Kim, Hyeji},
  title = {Residual Diffusion Models for Variable-Rate Joint Source–Channel Coding of MIMO CSI},
  journal = {IEEE Journal on Selected Areas in Communications},
  year = {2026},
  volume = {44},
  pages = {3620--3633},
  doi = {10.1109/jsac.2026.3666741}
}
Kostenlos starten →