用扩散模型实现任意电极位置的脑电超分辨率，通用性强且计算高效。
ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders
- 通过4D旋转位置编码建模时空结构，支持任意电极数量与位置
- 在208个数据集上训练，通道丢失率越高，性能越优于传统插值方法
- 可直接用于新数据集，适合脑电分析流水线部署
我们提出 exttt{ZUNA}，一个380M参数的掩码扩散自编码器，用于在任意电极数量和位置下进行脑电信号的掩码通道补全与超分辨率。该架构将多通道脑电分割为短时窗，并通过 (x,y,z,t) 的4维旋转位置编码注入时空结构，实现对任意电极子集和位置的推理。我们在涵盖208个公开数据集、约200万通道小时的聚合和谐数据集上，采用联合重建与高比例通道丢弃的目标进行训练。结果表明， exttt{ZUNA} 显著优于普遍使用的球面样条插值方法，且在更高通道丢失率下优势更明显。关键的是，相比同类深度学习方法， exttt{ZUNA} 的性能在不同数据集和电极位置间具有良好的泛化能力，可直接应用于新数据集与新问题。尽管具备生成能力， exttt{ZUNA} 仍保持部署实用性。我们开源了 Apache-2.0 许可的权重及兼容 MNE 的预处理/推理工具包，以促进可复现比较与下游脑电分析应用。
原文摘要 · Abstract (English)
We present \texttt{ZUNA}, a 380M-parameter masked diffusion autoencoder trained to perform masked channel infilling and superresolution for arbitrary electrode numbers and positions in EEG signals. The \texttt{ZUNA} architecture tokenizes multichannel EEG into short temporal windows and injects spatiotemporal structure via a 4D rotary positional encoding over (x,y,z,t), enabling inference on arbitrary channel subsets and positions. We train ZUNA on an aggregated and harmonized corpus spanning 208 public datasets containing approximately 2 million channel-hours using a combined reconstruction and heavy channel-dropout objective. We show that \texttt{ZUNA} substantially improves over ubiquitous spherical-spline interpolation methods, with the gap widening at higher dropout rates. Crucially, compared to other deep learning methods in this space, \texttt{ZUNA}'s performance \emph{generalizes} across datasets and channel positions allowing it to be applied directly to novel datasets and problems. Despite its generative capabilities, \texttt{ZUNA} remains computationally practical for deployment. We release Apache-2.0 weights and an MNE-compatible preprocessing/inference stack to encourage reproducible comparisons and downstream use in EEG analysis pipelines.
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。