EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience

TL;DR

This paper introduces EEG2Vision, an end-to-end framework for reconstructing visual stimuli from EEG signals, improving quality through multimodal diffusion and semantic boosting, even with low-density electrode setups.

Contribution

The novel EEG2Vision framework combines EEG-conditioned diffusion and multimodal language models to enhance image reconstruction from low-resolution EEG data.

Findings

Semantic decoding accuracy drops from 89% to 38% with fewer channels.

Reconstruction quality, measured by FID, slightly decreases with channel reduction.

Boosting improves perceptual metrics and user preference across all configurations.

Abstract

Reconstructing visual stimuli from non-invasive electroencephalography (EEG) remains challenging due to its low spatial resolution and high noise, particularly under realistic low-density electrode configurations. To address this, we present EEG2Vision, a modular, end-to-end EEG-to-image framework that systematically evaluates reconstruction performance across different EEG resolutions (128, 64, 32, and 24 channels) and enhances visual quality through a prompt-guided post-reconstruction boosting mechanism. Starting from EEG-conditioned diffusion reconstruction, the boosting stage uses a multimodal large language model to extract semantic descriptions and leverages image-to-image diffusion to refine geometry and perceptual coherence while preserving EEG-grounded structure. Our experiments show that semantic decoding accuracy degrades significantly with channel reduction (e.g., 50-way Top-1 Acc from 89% to 38%), while reconstruction quality slight decreases (e.g., FID from 76.77 to 80.51). The proposed boosting consistently improves perceptual metrics across all configurations, achieving up to 9.71% IS gains in low-channel settings. A user study confirms the clear perceptual preference for boosted reconstructions. The proposed approach significantly boosts the feasibility of real-time brain-2-image applications using low-resolution EEG devices, potentially unlocking this type of applications outside laboratory settings.