{"slug": "brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment", "title": "Brain-to-Image Retrieval and Reconstruction via Multimodal EEG Alignment", "summary": "Researchers have developed a brain-to-image system that decodes visual stimuli from EEG signals, achieving a mean Top-1 retrieval accuracy of 86.30% and a CLIP score of 0.903 for image reconstruction. The system uses multi-level blurring with EVNet features for retrieval and CognitionCapturerPro for reconstruction, aligning EEG representations with multi-modal CLIP embeddings. The findings demonstrate that modern multi-modal alignment and generative modeling can effectively decode rich visual representations from EEG signals.", "body_md": "arXiv:2605.23996v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment", "canonical_source": "https://arxiv.org/abs/2605.23996", "published_at": "2026-05-26 04:00:00+00:00", "updated_at": "2026-05-26 04:11:07.929092+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "generative-ai", "neural-networks"], "entities": ["EVNet", "InfoNCE", "CognitionCapturerPro", "CLIP", "SDXL-Turbo", "IP-Adapter", "ViT-H-14", "ViT-L/14"], "alternates": {"html": "https://wpnews.pro/news/brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment", "markdown": "https://wpnews.pro/news/brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment.md", "text": "https://wpnews.pro/news/brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment.txt", "jsonld": "https://wpnews.pro/news/brain-to-image-retrieval-and-reconstruction-via-multimodal-eeg-alignment.jsonld"}}