# Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning

arXiv: https://arxiv.org/abs/2407.03089 · HTML: https://mlsanity.com/paper/2407.03089/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 19 of its 57 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 19 of 19)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT](https://mlsanity.com/paper/2303.04226/) (2023)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [DreamDiffusion: Generating High-Quality Images from Brain EEG Signals](https://mlsanity.com/paper/2306.16934/) (2023)
- [Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis](https://mlsanity.com/paper/2008.03483/) (2020)
- [Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain](https://mlsanity.com/paper/2011.04145/) (2020)
- [Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction](https://mlsanity.com/paper/2107.09928/) (2021)
- [Morphological feature visualization of Alzheimer's disease via Multidirectional Perception GAN](https://mlsanity.com/paper/2111.12886/) (2021)
- [DecGAN: Decoupling Generative Adversarial Network detecting abnormal neural circuits for Alzheimer's disease](https://mlsanity.com/paper/2110.05712/) (2021)
- [Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection Segmentation System](https://mlsanity.com/paper/2209.02934/) (2022)
- [EEG Channel Interpolation Using Deep Encoder-decoder Netwoks](https://mlsanity.com/paper/2009.12244/) (2020)
- [Source Aware Deep Learning Framework for Hand Kinematic Reconstruction using EEG Signal](https://mlsanity.com/paper/2103.13862/) (2021)
- [LightSleepNet: Design of a Personalized Portable Sleep Staging System Based on Single-Channel EEG](https://mlsanity.com/paper/2401.13194/) (2024)

## Built on by (most cited first, 17 of 17)

- [Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution](https://mlsanity.com/paper/2510.19166/) (2025)
- [EEGDM: EEG Representation Learning via Generative Diffusion Model](https://mlsanity.com/paper/2508.14086/) (2025)
- [High-Fidelity Functional Ultrasound Reconstruction via A Visual Auto-Regressive Framework](https://mlsanity.com/paper/2505.21530/) (2025)
- [Transformer-based EEG Decoding: A Survey](https://mlsanity.com/paper/2507.02320/) (2025)
- [ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders](https://mlsanity.com/paper/2602.18478/) (2026)
- [Temporal and Spatial Super Resolution with Latent Diffusion Model in Medical MRI images](https://mlsanity.com/paper/2410.23898/) (2024)
- [ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging](https://mlsanity.com/paper/2505.22683/) (2025)
- [A Pre-trained Framework for Multilingual Brain Decoding Using Non-invasive Recordings](https://mlsanity.com/paper/2506.03214/) (2025)
- [Geometry- and Relation-Aware Diffusion for EEG Super-Resolution](https://mlsanity.com/paper/2602.02238/) (2026)
- [Empowering Functional Neuroimaging: A Pre-trained Generative Framework for Unified Representation of Neural Signals](https://mlsanity.com/paper/2506.02433/) (2025)
- [Multi-Masked Querying Network for Robust Emotion Recognition from Incomplete Multi-Modal Physiological Signals](https://mlsanity.com/paper/2507.20737/) (2025)
- [Spatial Imputation Drives Cross-Domain Alignment for EEG Classification](https://mlsanity.com/paper/2508.03437/) (2025)
- [Understanding Mental States in Active and Autonomous Driving with EEG](https://mlsanity.com/paper/2512.09190/) (2025)
- [DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting](https://mlsanity.com/paper/2603.16885/) (2026)
- [EMAG: Differentiable 4D Gaussian Mixture Splatting for EEG Spatial Super-Resolution](https://mlsanity.com/paper/2605.29731/) (2026)
- [TGSD: Topology-Guided State-Space Diffusion Framework for EEG Spatial Super-Resolution](https://mlsanity.com/paper/2606.03998/) (2026)
- [Coordinate-Queryable Neural Field Reconstruction for EEG Spatial Super-Resolution with Unseen-Electrode Generation](https://mlsanity.com/paper/2606.23707/) (2026)

## Abstract (arXiv)

Electroencephalogram (EEG) technology, particularly high-density EEG (HD EEG) devices, is widely used in fields such as neuroscience. HD EEG devices improve the spatial resolution of EEG by placing more electrodes on the scalp, which meet the requirements of clinical diagnostic applications such as epilepsy focus localization. However, this technique faces challenges, such as high acquisition costs and limited usage scenarios. In this paper, spatio-temporal adaptive diffusion models (STAD) are proposed to pioneer the use of diffusion models for achieving spatial SR reconstruction from low-resolution (LR, 64 channels or fewer) EEG to high-resolution (HR, 256 channels) EEG. Specifically, a spatio-temporal condition module is designed to extract the spatio-temporal features of LR EEG, which are then used as conditional inputs to direct the reverse denoising process. Additionally, a multi-scale Transformer denoising module is constructed to leverage multi-scale convolution blocks and cross-attention-based diffusion Transformer blocks for conditional guidance to generate subject-adaptive SR EEG. Experimental results demonstrate that the STAD significantly enhances the spatial resolution of LR EEG and quantitatively outperforms existing methods. Furthermore, STAD demonstrate their value by applying synthetic SR EEG to classification and source localization tasks, indicating their potential to substantially boost the spatial resolution of EEG.