SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

Wanli Ouyang (Shanghai AI Lab) · Dongzhan Zhou (Shanghai Artificial Intelligence Laboratory) · Weijian Mai (Shanghai Artificial Intelligence Laboratory, University of Hong Kong) · Jiamin Wu (The Chinese University of Hong Kong) · Yu Zhu (Institute of automation, Chinese academy of science) · Zhouheng Yao (Nanjing University) · Andrew Luo (University of Hong Kong) · Qihao Zheng (Shanghai Artificial Intelligence Laboratory) · Chunfeng Song (Shanghai Artificial Intelligence Laboratory)

biological variabilitybrainvaecomputational neurosciencecontinuous probability distributionsfew-shot datafmri synthesisfmri-to-image decodingfunctional consistencygenerative frameworkhemodynamic responsesneural response manifoldprobabilistic learningsemantic-to-neural mappervisual semantic constraintsvisual-to-neural mapping

Deciphering how visual stimuli are transformed into cortical responses is a fundamental challenge in computational neuroscience. This visual-to-neural mapping is inherently a one-to-many relationship, as identical visual inputs reliably evoke variable hemodynamic responses across trials, contexts, and subjects. However, existing deterministic methods struggle to simultaneously model this biological variability while capturing the underlying functional consistency that encodes stimulus information. To address these limitations, we propose SynBrain, a generative framework that simulates the transformation from visual semantics to neural responses in a probabilistic and biologically interpretable manner. SynBrain introduces two key components: (i) BrainVAE models neural representations as continuous probability distributions via probabilistic learning while maintaining functional consistency through visual semantic constraints; (ii) A Semantic-to-Neural Mapper acts as a semantic transmission pathway, projecting visual semantics into the neural response manifold to facilitate high-fidelity fMRI synthesis. Experimental results demonstrate that SynBrain surpasses state-of-the-art methods in subject-specific visual-to-fMRI encoding performance. Furthermore, SynBrain adapts efficiently to new subjects with few-shot data and synthesizes high-quality fMRI signals that are effective in improving data-limited fMRI-to-image decoding performance. Beyond that, SynBrain reveals functional consistency across trials and subjects, with synthesized signals capturing interpretable patterns shaped by biological neural variability. Our code is available at https://github.com/MichaelMaiii/SynBrain.