DiffTAC: Temporal-Conditioned Latent Diffusion with Integrated Attention for Intermediate Frame Generation and Temporal Super-Resolution in Cardiac MRI

Shilajit Banerjee, Aniruddha Sinha

Keywords: Cardiac MRI, Frame Interpolation, Diffusion Models, Cross-Attention, Latent Space, Temporal Consistency

TL;DR: A diffusion-based model for generating intermediate cardiac phases using learnable temporal embeddings and cross-attention conditioning

Abstract: Cardiac MRI captures dynamic cardiac motion, yet its temporal resolution remains fundamentally constrained by long acquisition times and breath-hold requirements. We introduce DiffTAC, a latent diffusion framework that synthesizes intermediate cardiac phases by treating time as an explicit conditioning variable. Using the end-diastolic (ED) and end-systolic (ES) frames as anatomical anchors, DiffTAC performs denoising in the latent space of a pretrained variational autoencoder and conditions generation on a learnable temporal embedding that specifies the desired phase location within the cardiac cycle. To effectively fuse temporal conditioning with anatomical context, we propose the Integrated Attention Block (IAB), a unified module that combines self-attention and cross-attention to modulate spatial features according to the target temporal position. This design enables the model to synthesize anatomically coherent, temporally smooth intermediate frames. Experiments on the multiple publicly available datasets demonstrate that DiffTAC produces highly realistic intermediate phases and achieves superior temporal consistency compared to classical interpolation, optical-flow–based reconstruction, and ablated variants of our architecture. These findings show that modeling time as a conditioning signal within a diffusion framework provides an effective and acquisition-free solution for temporal super-resolution in cardiac MRI.

Primary Subject Area: Image Synthesis

Secondary Subject Area: Application: Cardiology

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 37