TROI learns a sparse brain-voxel mask from one hour of a new subject's fMRI data and improves several retrieval metrics over a MindEye2 baseline that uses manual ROIs.
Reconstructing the mind’s eye: fmri-to-image with contrastive learning and diffusion priors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding
TROI learns a sparse brain-voxel mask from one hour of a new subject's fMRI data and improves several retrieval metrics over a MindEye2 baseline that uses manual ROIs.