Home | Publications | YYZ+25

FB-Diff: Fourier Basis-Guided Diffusion for Temporal Interpolation of 4D Medical Imaging

MCML Authors

Abstract

The temporal interpolation task for 4D medical imaging, plays a crucial role in clinical practice of respiratory motion modeling. Following the simplified linear-motion hypothesis, existing approaches adopt optical flow-based models to interpolate intermediate frames. However, realistic respiratory motions should be nonlinear and quasi-periodic with specific frequencies. Intuited by this property, we resolve the temporal interpolation task from the frequency perspective, and propose a F ourier B asis-guided Diff usion model, termed FB-Diff. Specifically, due to the regular motion discipline of respiration, physiological motion priors are introduced to describe general characteristics of temporal data distributions. Then a Fourier motion operator is elaborately devised to extract Fourier bases by incorporating physiological motion priors and case-specific spectral information in the feature space of Variational Autoencoder. Well-learned Fourier bases can better simulate respiratory motions with motion patterns of specific frequencies. Conditioned on starting and ending frames, the diffusion model further leverages well-learned Fourier bases via the basis interaction operator, which promotes the temporal interpolation task in a generative manner. Extensive results demonstrate that FB-Diff achieves state-of-the-art (SOTA) perceptual performance with better temporal consistency while maintaining promising reconstruction metrics.

inproceedings YYZ+25

ICCV 2025

IEEE/CVF International Conference on Computer Vision. Honolulu, Hawai'i, Oct 19-23, 2025.
Conference logo
A* Conference

Authors

X. You • R. Yang • C. Zhang • Z. Jiang • J. Yang • N. Navab

Links

DOI

Research Area

 C1 | Medicine

BibTeXKey: YYZ+25

#p-navab
Back to Top