发表机构
Zhejiang University; Inha University; Singapore University of Technology and Design; The University of Hong Kong（浙江大学; 仁荷大学; 新加坡科技设计大学; 香港大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对FDD大规模MIMO系统CSI反馈开销大的问题，提出LRP引导的CSI反馈框架，结合DCRNetV2实现更优的精度-复杂度权衡，性能优于现有基准方法。
AI 中文摘要
下行链路信道状态信息（CSI）反馈是频分双工（FDD）大规模多输入多输出（MIMO）系统中波束成形优化的关键环节。然而，反馈开销会随天线数量和子载波数量的增加而上升，这给实际部署带来了重大挑战。尽管近期基于深度学习（DL）的方法通过在用户设备（UE）侧压缩CSI并在基站（BS）侧重构CSI来降低该开销，但大多数此类方法将CSI视为普通图像，依赖卷积或Transformer架构，导致低秩多径先验未得到充分利用，且在UE和BS侧均引入了不可忽视的计算量。为解决该问题，我们提出了一种低秩先验（LRP）引导的CSI反馈框架，该框架直接对秩一信道分量执行结构化感知与重构。具体而言，LRP编码器在UE侧执行可学习的秩一感知以获取路径感知测量值，而LRP解码器在BS侧通过秩一合成重构CSI，避免了经典求解器所需的迭代恢复。为补偿有限秩近似残差，我们将之前的DCRNet扩展为DCRNetV2，方法是融入所提出的LRP骨干网络和门控膨胀卷积残差分支。在多个数据集和场景上的实验表明，所提方法相较于现有基于模型和基于DL的基准方法，实现了更优的精度-复杂度权衡。特别地，独立的LRP相较于基于模型的基准方法，实现了超过10 dB的归一化均方误差（NMSE）提升，且复杂度低得多；而DCRNetV2则达到了与最先进的基于Transformer的方法相当的精度，复杂度仅为其约五分之一。源代码可在该https URL获取。
英文摘要
Downlink channel state information (CSI) feedback is essential for beamforming optimization in frequency-division duplex (FDD) massive multiple-input multiple-output (MIMO) systems. However, the feedback overhead increases with the number of antennas and subcarriers, posing a major challenge to practical deployment. Although recent deep learning (DL)-based methods reduce this overhead by compressing CSI at the user equipment (UE) and reconstructing it at the base station (BS), most of them treat CSI as a generic image and rely on convolutional or Transformer architectures. As a result, the low-rank multipath prior is insufficiently exploited, while non-negligible computation is introduced at both the UE and the BS. To address this issue, we propose a low-rank prior (LRP)-guided CSI feedback framework that performs structured sensing and reconstruction directly over rank-one channel components. Specifically, the LRP encoder conducts learnable rank-one sensing to obtain path-aware measurements at the UE, while the LRP decoder reconstructs CSI through rank-one synthesis at the BS, avoiding the iterative recovery required by classical solvers. To compensate for finite-rank approximation residuals, we extend our previous DCRNet into DCRNetV2 by incorporating the proposed LRP backbone and gated dilated-convolutional residual branches. Experiments on multiple datasets and scenarios show that the proposed methods achieve a better accuracy-complexity tradeoff than existing model-based and DL-based baselines. In particular, standalone LRP achieves more than $10$~dB NMSE improvement over model-based baselines with much lower complexity, while DCRNetV2 achieves comparable accuracy to state-of-the-art Transformer-based methods with only about one-fifth of the complexity. The source code is available at https://github.com/tangshunpu/DCRNetV2.
