Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moradi, Mohammad, Moradi, Morteza, Grassia, Marco, Mangioni, Giuseppe
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914466945302528
author Moradi, Mohammad
Moradi, Morteza
Grassia, Marco
Mangioni, Giuseppe
author_facet Moradi, Mohammad
Moradi, Morteza
Grassia, Marco
Mangioni, Giuseppe
contents Recent progress in brain-guided image generation has improved the quality of fMRI-based reconstructions; however, fundamental challenges remain in preserving object-level structure and semantic fidelity. Many existing approaches overlook the spatial arrangement of salient objects, leading to conceptually inconsistent outputs. We propose a saliency-driven decoding framework that employs graph-informed saliency priors to translate structural cues from brain signals into spatial masks. These masks, together with semantic information extracted from embeddings, condition a diffusion model to guide image regeneration, helping preserve object conformity while maintaining natural scene composition. In contrast to pipelines that invoke multiple diffusion stages, our approach relies on a single frozen model, offering a more lightweight yet effective design. Experiments show that this strategy improves both conceptual alignment and structural similarity to the original stimuli, while also introducing a new direction for efficient, interpretable, and structurally grounded brain decoding.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10617
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding
Moradi, Mohammad
Moradi, Morteza
Grassia, Marco
Mangioni, Giuseppe
Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
Recent progress in brain-guided image generation has improved the quality of fMRI-based reconstructions; however, fundamental challenges remain in preserving object-level structure and semantic fidelity. Many existing approaches overlook the spatial arrangement of salient objects, leading to conceptually inconsistent outputs. We propose a saliency-driven decoding framework that employs graph-informed saliency priors to translate structural cues from brain signals into spatial masks. These masks, together with semantic information extracted from embeddings, condition a diffusion model to guide image regeneration, helping preserve object conformity while maintaining natural scene composition. In contrast to pipelines that invoke multiple diffusion stages, our approach relies on a single frozen model, offering a more lightweight yet effective design. Experiments show that this strategy improves both conceptual alignment and structural similarity to the original stimuli, while also introducing a new direction for efficient, interpretable, and structurally grounded brain decoding.
title Brain-Grasp: Graph-based Saliency Priors for Improved fMRI-based Visual Brain Decoding
topic Image and Video Processing
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2604.10617