Problem
Research questions and friction points this paper is trying to address.
EEG spatial super-resolution
high-density EEG
low-density EEG
brain source reconstruction
scalp EEG
EMAG: Differentiable 4D Gaussian Mixture Splatting for EEG Spatial Super-Resolution
🤖 AI Summary
High-density electroencephalography (HD-EEG) remains challenging to deploy widely due to its high cost and complex setup. This work proposes an end-to-end differentiable EEG spatial super-resolution method that models neural sources as an anisotropic 4D spatiotemporal Gaussian mixture, introducing for the first time a full 4×4 precision matrix representation to explicitly couple spatial and temporal dimensions. By integrating differentiable Gaussian field rendering with spherical brain mesh parameterization, the approach reconstructs and visualizes high-density EEG signals without requiring ground-truth source localization supervision. Evaluated on the Localize-MI, SEED, and SEED-IV benchmarks, the method outperforms state-of-the-art approaches across most super-resolution scales and enables intuitive interpretation of underlying neural source configurations.
📝 Abstract
High-density electroencephalography (HD-EEG) enables fine-grained measurement of cortical activity but requires expensive hardware and lengthy setup times, limiting its clinical and research accessibility. We propose EMAG (EEG Mixture of Anisotropic Gaussians), a differentiable framework that reconstructs HD-EEG signals from a sparse subset of low-density (LD) electrodes by representing brain electrical sources as a mixture of anisotropic 4D space-time Gaussians. EMAG places a mixture of multiple Gaussians at each point of a spherical brain grid, each parameterized by a full 4 x 4 precision matrix, enabling anisotropic spatial spreads and explicit coupling between spatial and temporal dimensions. The forward model renders scalp EEG via differentiable Gaussian field contributions at electrode locations, enabling end-to-end training without explicit source localization supervision. We evaluate EMAG on three public EEG benchmarks (Localize-MI, SEED, and SEED-IV) at super-resolution factors of 2x through 8/16x. EMAG outperforms the current state-of-the-art EEG super-resolution method at most super-resolution factors on three standard benchmarks (Localize-MI, SEED, SEED-IV). The explicit Gaussian parameterization further enables direct visualization and interpretability of learned brain source configurations, potentially opening avenues for clinical and neuroscientific applications, such as source localization or biomarker discovery.
Innovation
Methods, ideas, or system contributions that make the work stand out.
differentiable rendering
4D Gaussian mixture
anisotropic spatio-temporal modeling
EEG super-resolution
interpretable source representation
🔎 Similar Papers
No similar papers found.
