MindDiffuser is a two-stage framework that improves semantic and structural fidelity in reconstructing visual stimuli from fMRI, EEG, and MEG signals using CLIP embeddings and Stable Diffusion with backpropagation refinement.
IEEE Transactions on Medical Imaging, 1–1 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Versatile Framework with Semantic and Structural guidance for Image Reconstruction from Brain Activity
MindDiffuser is a two-stage framework that improves semantic and structural fidelity in reconstructing visual stimuli from fMRI, EEG, and MEG signals using CLIP embeddings and Stable Diffusion with backpropagation refinement.