Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) a novel sphere tokenizer that explicitly models fMRI signals as spatially coherent 2D spherical data on the cortical surface; (2) integration of structural MRI (sMRI) data, enabling personalized encoding of individual anatomical variations; and (3) a positive-sample mixup strategy for efficiently leveraging multiple fMRI scans associated with the same visual stimulus. Collectively, these innovations enhance reconstruction accuracy, biological interpretability, and generalizability across individuals. Experiments demonstrate superior reconstruction performance compared to SOTA methods, highlighting the effectiveness and interpretability of our biologically informed approach.
@article{arxiv.2507.16389,
title = {From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure},
author = {Sijin Yu and Zijiao Chen and Wenxuan Wu and Shengxian Chen and Zhongliang Liu and Jingxin Nie and Xiaofen Xing and Xiangmin Xu and Xin Zhang},
journal= {arXiv preprint arXiv:2507.16389},
year = {2025}
}