{"ID":2851595,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20855","arxiv_id":"2510.20855","title":"BrainCognizer: Brain Decoding with Human Visual Cognition Simulation for fMRI-to-Image Reconstruction","abstract":"Brain decoding is a key neuroscience field that reconstructs the visual stimuli from brain activity with fMRI, which helps illuminate how the brain represents the world. fMRI-to-image reconstruction has achieved impressive progress by leveraging diffusion models. However, brain signals infused with prior knowledge and associations exhibit a significant information asymmetry when compared to raw visual features, still posing challenges for decoding fMRI representations under the supervision of images. Consequently, the reconstructed images often lack fine-grained visual fidelity, such as missing attributes and distorted spatial relationships. To tackle this challenge, we propose BrainCognizer, a novel brain decoding model inspired by human visual cognition, which explores multi-level semantics and correlations without fine-tuning of generative models. Specifically, BrainCognizer introduces two modules: the Cognitive Integration Module which incorporates prior human knowledge to extract hierarchical region semantics; and the Cognitive Correlation Module which captures contextual semantic relationships across regions. Incorporating these two modules enhances intra-region semantic consistency and maintains inter-region contextual associations, thereby facilitating fine-grained brain decoding. Moreover, we quantitatively interpret our components from a neuroscience perspective and analyze the associations between different visual patterns and brain functions. Extensive quantitative and qualitative experiments demonstrate that BrainCognizer outperforms state-of-the-art approaches on multiple evaluation metrics.","short_abstract":"Brain decoding is a key neuroscience field that reconstructs the visual stimuli from brain activity with fMRI, which helps illuminate how the brain represents the world. fMRI-to-image reconstruction has achieved impressive progress by leveraging diffusion models. However, brain signals infused with prior knowledge and...","url_abs":"https://arxiv.org/abs/2510.20855","url_pdf":"https://arxiv.org/pdf/2510.20855v1","authors":"[\"Guoying Sun\",\"Weiyu Guo\",\"Tong Shao\",\"Yang Yang\",\"Haijin Zeng\",\"Jie Liu\",\"Jingyong Su\"]","published":"2025-10-22T08:25:43Z","proceeding":"q-bio.NC","tasks":"[\"q-bio.NC\"]","methods":"[\"Diffusion Model\"]","has_code":false}