Geometry- and Relation-Aware Diffusion for EEG Super-Resolution

• URL: http://arxiv.org/abs/2602.02238v1
• Date: Mon, 02 Feb 2026 15:44:20 GMT
• Title: Geometry- and Relation-Aware Diffusion for EEG Super-Resolution
• Authors: Laura Yao, Gengwei Zhang, Moajjem Chowdhury, Yunmei Liu, Tianlong Chen,
• Abstract summary: TopoDiff is a geometry- and relation-aware diffusion model for EEG spatial super-resolution.<n>Inspired by how human experts interpret spatial EEG patterns, TopoDiff incorporates topology-aware image embeddings.<n>This design yields a spatially grounded EEG spatial super-resolution framework with consistent performance improvements.
• Score: 33.53397341962788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent electroencephalography (EEG) spatial super-resolution (SR) methods, while showing improved quality by either directly predicting missing signals from visible channels or adapting latent diffusion-based generative modeling to temporal data, often lack awareness of physiological spatial structure, thereby constraining spatial generation performance. To address this issue, we introduce TopoDiff, a geometry- and relation-aware diffusion model for EEG spatial super-resolution. Inspired by how human experts interpret spatial EEG patterns, TopoDiff incorporates topology-aware image embeddings derived from EEG topographic representations to provide global geometric context for spatial generation, together with a dynamic channel-relation graph that encodes inter-electrode relationships and evolves with temporal dynamics. This design yields a spatially grounded EEG spatial super-resolution framework with consistent performance improvements. Across multiple EEG datasets spanning diverse applications, including SEED/SEED-IV for emotion recognition, PhysioNet motor imagery (MI/MM), and TUSZ for seizure detection, our method achieves substantial gains in generation fidelity and leads to notable improvements in downstream EEG task performance.

Related papers

• Region-aware Spatiotemporal Modeling with Collaborative Domain Generalization for Cross-Subject EEG Emotion Recognition [15.65302580686776]
  Cross-subject EEG-based emotion recognition is challenging due to strong inter-subject variability.<n>We propose a Region-aware Spatiotemporal Modeling framework with Collaborative Domain Generalization for emotion recognition.<n>RSM-CoDG incorporates priors derived from functional brain region partitioning to construct region-level spatial representations.<n>It also employs multi-scale temporal modeling to characterize the dynamic evolution of emotion-evoked neural activity.
  arXiv  Detail & Related papers  (2026-01-22T03:35:40Z)
• Graph-Based Learning of Spectro-Topographical EEG Representations with Gradient Alignment for Brain-Computer Interfaces [31.418253191692756]
  We present a novel graph-based learning of EEG representations with gradient alignment (GEEGA)<n>Our model leverages graph convolutional networks to fuse embeddings from frequency-based topographical maps and time-frequency spectrograms.<n>We validate the efficacy of our method through extensive experiments on three publicly available EEG datasets.
  arXiv  Detail & Related papers  (2025-12-08T18:54:11Z)
• EEG-Driven Image Reconstruction with Saliency-Guided Diffusion Models [4.815274507478168]
  Existing EEG-driven image reconstruction methods often overlook spatial attention mechanisms, limiting fidelity and semantic coherence.<n>We propose a dual-conditioning framework that combines EEG embeddings with spatial saliency maps to enhance image generation.
  arXiv  Detail & Related papers  (2025-10-30T11:34:37Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing [49.243031514520794]
  Large Language Models (LLMs) excel at capturing long-range signals due to their text-centric design.<n>PhysLLM achieves state-the-art accuracy and robustness, demonstrating superior generalization across lighting variations and motion scenarios.
  arXiv  Detail & Related papers  (2025-05-06T15:18:38Z)
• Geometry-aware Active Learning of Spatiotemporal Dynamic Systems [4.251030047034566]
  This paper proposes a geometry-aware active learning framework for modeling dynamic systems.<n>We develop an adaptive active learning strategy to strategically identify spatial locations for data collection and further maximize the prediction accuracy.
  arXiv  Detail & Related papers  (2025-04-26T19:56:38Z)
• EEG2GAIT: A Hierarchical Graph Convolutional Network for EEG-based Gait Decoding [8.529597745689195]
  Decoding gait dynamics from EEG signals presents significant challenges due to the complex spatial dependencies of motor processes.<n>We propose EEG2GAIT, a novel hierarchical graph-based model that captures multi-level spatial embeddings of EEG channels.<n>We also contribute a new Gait-EEG dataset, consisting of synchronized EEG and lower-limb joint angle data collected from 50 participants over two lab visits.
  arXiv  Detail & Related papers  (2025-04-02T07:48:21Z)
• Exploring Representation-Aligned Latent Space for Better Generation [86.45670422239317]
  We introduce ReaLS, which integrates semantic priors to improve generation performance.<n>We show that fundamental DiT and SiT trained on ReaLS can achieve a 15% improvement in FID metric.<n>The enhanced semantic latent space enables more perceptual downstream tasks, such as segmentation and depth estimation.
  arXiv  Detail & Related papers  (2025-02-01T07:42:12Z)
• Geometric Trajectory Diffusion Models [58.853975433383326]
  Generative models have shown great promise in generating 3D geometric systems. Existing approaches only operate on static structures, neglecting the fact that physical systems are always dynamic in nature. We propose geometric trajectory diffusion models (GeoTDM), the first diffusion model for modeling the temporal distribution of 3D geometric trajectories.
  arXiv  Detail & Related papers  (2024-10-16T20:36:41Z)
• MVGT: A Multi-view Graph Transformer Based on Spatial Relations for EEG Emotion Recognition [4.184462746475896]
  We introduce a multi-view graph transformer (MVGT) based on spatial relations that integrates information across three domains.<n> evaluation on publicly available datasets demonstrates that MVGT surpasses state-of-the-art methods in performance.
  arXiv  Detail & Related papers  (2024-07-03T14:13:00Z)
• Generative AI Enables EEG Super-Resolution via Spatio-Temporal Adaptive Diffusion Learning [29.478652556789104]
  HD devices improve the spatial resolution of the EEG by placing more electrodes on the scalp.<n>This technique enhances challenges such as high acquisition costs and limited usage scenarios.<n>In this paper, adaptive diffusion models (STAD) are proposed to pioneer use of diffusion models for achieving spatial reconstruction.
  arXiv  Detail & Related papers  (2024-07-03T13:26:31Z)
• Physics-Inspired Degradation Models for Hyperspectral Image Fusion [61.743696362028246]
  Most fusion methods solely focus on the fusion algorithm itself and overlook the degradation models. We propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI. Our proposed PIDM can boost the fusion performance of existing fusion methods in practical scenarios.
  arXiv  Detail & Related papers  (2024-02-04T09:07:28Z)
• On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition [97.14064057840089]
  Graphal networks (GCNs) promising performance in skeleton-based human action recognition by modeling a sequence of skeletons as a graph. Most of the recently proposed G-temporal-based methods improve the performance by learning the graph structure at each layer of the network.
  arXiv  Detail & Related papers  (2020-11-07T19:03:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.