# T2I-Diff: fMRI Signal Generation via Time-Frequency Image Transform and Classifier-Free Denoising Diffusion Models

arXiv: https://arxiv.org/abs/2509.20822 · HTML: https://mlsanity.com/paper/2509.20822/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 19 of 19)

- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [Diffusion Models for Time Series Applications: A Survey](https://mlsanity.com/paper/2305.00624/) (2023)
- [COT-GAN: Generating Sequential Data via Causal Optimal Transport](https://mlsanity.com/paper/2006.08571/) (2020)
- [On the Constrained Time-Series Generation Problem](https://mlsanity.com/paper/2307.01717/) (2023)
- [Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series](https://mlsanity.com/paper/2410.19538/) (2024)
- [Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification](https://mlsanity.com/paper/2107.12838/) (2021)
- [Graph-Regularized Manifold-Aware Conditional Wasserstein GAN for Brain Functional Connectivity Generation](https://mlsanity.com/paper/2212.05316/) (2022)
- [Diffusion Models for Computational Neuroimaging: A Survey](https://mlsanity.com/paper/2502.06552/) (2025)
- [Separating Stimulus-Induced and Background Components of Dynamic Functional Connectivity in Naturalistic fMRI](https://mlsanity.com/paper/2102.10331/) (2021)
- [A Deep Probabilistic Spatiotemporal Framework for Dynamic Graph Representation Learning with Application to Brain Disorder Identification](https://mlsanity.com/paper/2302.07243/) (2023)
- [KANS: Knowledge Discovery Graph Attention Network for Soft Sensing in Multivariate Industrial Processes](https://mlsanity.com/paper/2501.02015/) (2025)
- [ST-HCSS: Deep Spatio-Temporal Hypergraph Convolutional Neural Network for Soft Sensing](https://mlsanity.com/paper/2501.02016/) (2025)
- [Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching](https://mlsanity.com/paper/2504.16262/) (2025)

## Built on by (most cited first, 3 of 3)

- [Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification](https://mlsanity.com/paper/2605.30387/) (2026)
- [Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics](https://mlsanity.com/paper/2606.11833/) (2026)
- [FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model](https://mlsanity.com/paper/2609.34354/) (2026)

## Abstract (arXiv)

Functional Magnetic Resonance Imaging (fMRI) is an advanced neuroimaging method that enables in-depth analysis of brain activity by measuring dynamic changes in the blood oxygenation level-dependent (BOLD) signals. However, the resource-intensive nature of fMRI data acquisition limits the availability of high-fidelity samples required for data-driven brain analysis models. While modern generative models can synthesize fMRI data, they often underperform because they overlook the complex non-stationarity and nonlinear BOLD dynamics. To address these challenges, we introduce T2I-Diff, an fMRI generation framework that leverages time-frequency representation of BOLD signals and classifier-free denoising diffusion. Specifically, our framework first converts BOLD signals into windowed spectrograms via a time-dependent Fourier transform, capturing both the underlying temporal dynamics and spectral evolution. Subsequently, a classifier-free diffusion model is trained to generate class-conditioned frequency spectrograms, which are then reverted to BOLD signals via inverse Fourier transforms. Finally, we validate the efficacy of our approach by demonstrating improved accuracy and generalization in downstream fMRI-based brain network classification.