D$^2$-FOSA：双扩散引导的频域语义对齐脑电到图像重建
D$^2$-FOSA: Dual-Diffusion Guided EEG-to-Image Reconstruction with Frequency-Oriented Semantic Alignment
论文提出的双扩散潜变量生成器（DDLG）与频域导向的Mamba编码器，为跨模态生成（如EEG到图像）提供了可复用的双向条件扩散框架和频域特征建模思路，可启发视觉-脑信号对齐及基于扩散的语义重建研究。
原文依据 we propose D^2-FOSA, a unified dual-diffusion guided framework with frequency-oriented semantic alignment
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从脑电图（EEG）信号中重建视觉语义能够加深对人类视觉认知的理解，并支持下一代脑机接口（BCI）应用。尽管近年来取得了显著进展，但大多数现有的EEG编码器仍难以捕捉反映感知与认知节律的频率特异性神经动力学。此外，EEG与视觉内容之间的跨模态对齐仍未得到充分解决，导致语义一致性和视觉保真度有限。为解决这些问题，我们提出了D^2-FOSA，一个统一的、具有频域导向语义对齐的双扩散引导框架，它增强了频率感知的EEG表征，以实现语义更对齐的图像重建。具体而言，我们设计了一个基于频域导向Mamba（FOMamba）的频率-时空动力学编码器（FSTDE），以显式建模EEG信号中的振荡模式和长程依赖关系。随后，提取的特征通过对比学习被拉入CLIP对齐的视觉语义空间。同时，设计了一个具有双向EEG-图像条件作用的双扩散潜变量生成器（DDLG），以强制跨模态对齐并促进循环一致的生成。在四个具有挑战性的数据集上进行的大量实验表明，我们提出的D^2-FOSA在检索和重建任务上均显著优于现有方法。特别是，在THINGS-EEG的重建任务中，我们的D^2-FOSA在弗雷歇初始距离（FID）上比当代的MB2C方法高出17以上，表明感知保真度有了实质性提升。源代码见补充材料。
英文原文摘要 1692 字符
Reconstructing visual semantics from Electroencephalography (EEG) signals enables a deeper understanding of human visual cognition and supports next-generation brain-computer interface (BCI) applications.Despite notable advances in recent years, most existing EEG encoders still struggle to capture the frequency-specific neural dynamics that reflect perceptual and cognitive rhythms. Moreover, the cross-modal alignment between EEG and visual content remains insufficiently tackled, leading to limited semantic consistency and visual fidelity. To address these issues, we propose D^2-FOSA, a unified dual-diffusion guided framework with frequency-oriented semantic alignment, which strengthens the frequency-aware EEG representation for more semantically aligned image reconstruction.Specifically, we design a Frequency-Spatio-Temporal Dynamics Encoder (FSTDE) based on the Frequency-Oriented Mamba (FOMamba) to explicitly model oscillatory patterns and long-range dependencies in EEG signals. The extracted features are then pulled into the CLIP-aligned visual semantic space via contrastive learning.Meanwhile, a Dual Diffusion Latent Generator (DDLG) with bidirectional EEG-image conditioning is designed to enforce cross-modal alignment and promote cycle-consistent generation.Extensive experiments on four challenging datasets demonstrate that our proposed D^2-FOSA significantly outperforms existing methods in both retrieval and reconstruction tasks. Particularly, our D^2-FOSA surpasses the contemporary MB2C method by over 17 FID in the reconstruction task on THINGS-EEG, indicating a substantial improvement in perceptual fidelity. The source code is in the supplementary material.