用扩散模型修复5G信道数据，抗干扰能力强，适合稀疏信号场景。
Robust Super-Capacity SRS Channel Inpainting via Diffusion Models
- 引入似然梯度项融合系统知识，实现单模型跨条件自适应
- 在复杂干扰下性能提升达14 dB NMSE，匹配场景也保持高效
- 适用于5G NR中稀疏非均匀导频设计，鲁棒性优于传统方法
精确的信道状态信息对多用户MIMO系统至关重要。在5G NR中，基于互易性的上行导频参考信号（SRS）波束成形受资源与覆盖限制，促使采用稀疏非均匀的SRS分配。以往基于掩码自编码器（MAE）的方法虽提升了覆盖范围，但对训练掩码过拟合，在未见失真（如额外遮蔽、干扰、截断、非高斯噪声）下性能下降。本文提出一种基于扩散模型的信道补全框架，通过在推理阶段引入似然梯度项融合系统模型知识，使单一训练模型可适应多种不匹配条件。在标准CDL信道上，基于得分函数的扩散模型始终优于UNet得分模型基线和单步MAE，在分布偏移下表现更优，极端情况（如拉普拉斯噪声、用户干扰）下NMSE改善最高达14 dB，同时在匹配条件下仍保持竞争力。结果表明，扩散引导的补全是5G NR中超容量SRS设计的一种鲁棒且泛化能力强的方法。
原文摘要 · Abstract (English)
Accurate channel state information (CSI) is essential for reliable multiuser MIMO operation. In 5G NR, reciprocity-based beamforming via uplink Sounding Reference Signals (SRS) face resource and coverage constraints, motivating sparse non-uniform SRS allocation. Prior masked-autoencoder (MAE) approaches improve coverage but overfit to training masks and degrade under unseen distortions (e.g., additional masking, interference, clipping, non-Gaussian noise). We propose a diffusion-based channel inpainting framework that integrates system-model knowledge at inference via a likelihood-gradient term, enabling a single trained model to adapt across mismatched conditions. On standardized CDL channels, the score-based diffusion variant consistently outperforms a UNet score-model baseline and the one-step MAE under distribution shift, with improvements up to 14 dB NMSE in challenging settings (e.g., Laplace noise, user interference), while retaining competitive accuracy under matched conditions. These results demonstrate that diffusion-guided inpainting is a robust and generalizable approach for super-capacity SRS design in 5G NR systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。