MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data

MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data Paul S. Scotti 1,2 , Mihir Tripathy †2 , Cesar Kadir Torrico Villanueva †2 , Reese Kneeland †3 , Tong Chen 4,2 , Ashutosh Narang 2 , Charan Santhirasegaran 2 , Jonathan Xu 5,2 , Thomas Naselaris 3 , Kenneth A. Norman 6 , Tanishq Mathew Abraham 1,2 1 Stability AI , 2 Medical AI Research Center (MedARC) , 3 University of Minnesota, 4 The University of Sydney, 5 University of Waterloo, 6 Princeton Neuroscience Institute. († indicates core contribution)

saved by

• HudZah
• Lydia Nottingham

related reading

• [2305.18274] Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorsarxiv.org
• Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorsmedarc-ai.github.io
• Retrieving and reconstructing conceptually similar images from fMRI with latent diffusion models and a neuro-inspired brain decoding model - IOPscienceiopscience.iop.org
• Replicate - Run AI with an APIreplicate.com
• [2506.06898] NSD-Imagery: A benchmark dataset for extending fMRI vision decoding methods to mental imageryarxiv.org
• GitHub - nkmjm/mental_img_recon: Mental image reconstruction from human brain activity · GitHubgithub.com
• Attentionally modulated subjective images reconstructed from brain activity | bioRxivbiorxiv.org
• MinD-Vismind-vis.github.io
• Frontiers | End-to-End Deep Image Reconstruction From Human Brain Activityfrontiersin.org
• Sélection de votre établissementwww-sciencedirect-com.ezproxy.universite-paris-saclay.fr
• Frontiers | Natural Image Reconstruction From fMRI Using Deep Learning: A Surveyfrontiersin.org
• A massive 7T fMRI dataset to bridge cognitive neuroscience and artificial intelligence | Nature Neurosciencenature.com