# Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment

Source: [Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment](<https://www.sota2.com/research/paper/6a152902dbd7150506f7ddd8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-27T05:00:05.520Z

Authors: Chi Kit Wong, Yan Liu, Haowen Yan

Published: 2026-05-18T05:33:44.000Z

## Abstract

We present a brain-to-image system that decodes visual stimuli from EEG signals recorded during natural image viewing. Our system addresses two tasks: (1) EEG-to-image retrieval, which ranks the correct stimulus image among 200 candidates given an EEG segment, and (2) EEG-to-image reconstruction, which generates an image consistent with the perceived stimulus. For retrieval, we implement a multi-level blurring approach improved with biologically inspired EVNet features and trained with the InfoNCE loss. Evaluated over 10 random seeds for a single subject, the retrieval model achieves a mean final-epoch Top-1 accuracy of 86.30% and Top-5 accuracy of 98.55%. For reconstruction, we implement CognitionCapturerPro, which aligns EEG representations to multi-modal CLIP embeddings, including image, text, depth, and edge embeddings, and synthesizes images with SDXL-Turbo conditioned via IP-Adapter. Averaged over 10 seeds, the reconstruction model achieves a CLIP score of 0.903 using ViT-H-14, a CLIP score of 0.870 using ViT-L/14, and an SSIM of 0.409. These results demonstrate the feasibility of decoding rich visual representations from EEG signals using modern multi-modal alignment and generative modeling techniques.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [EEG-to-Image Retrieval on THINGS-EEG2 (train)](<https://www.sota2.com/research/sota/eeg-to-image-retrieval-on-things-eeg2-train.md>): EEG-to-Image Retrieval; THINGS-EEG2 (train); Top-1 Accuracy: 89.6.

- [EEG-to-Image Reconstruction on THINGS-EEG2 200-sample (test)](<https://www.sota2.com/research/sota/eeg-to-image-reconstruction-on-things-eeg2-200-sample-test.md>): EEG-to-Image Reconstruction; THINGS-EEG2 200-sample (test); CLIP-L/14 Two-way ID: 0.87.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.23996>)

[PDF](<https://arxiv.org/pdf/2605.23996.pdf>)