Part III: From Theory to Scientific Applications
2025 Tutorial
in
Tutorial: Harnessing Low Dimensionality in Diffusion Models: From Theory to Practice
in
Tutorial: Harnessing Low Dimensionality in Diffusion Models: From Theory to Practice
Abstract
We will advance diffusion models for scientific imaging by improving their flexibility, efficiency, and robustness in solving inverse problems on high-dimensional, high-resolution data. Our focus includes efficient latent and patch-based methods, enhanced data consistency for challenging 3D tasks, and controllable sampling techniques that enforce desired constraints while maintaining sample quality.
Video
Chat is not available.
Successful Page Load