Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models
Unlocking latent anatomical atlases from generative diffusion models through novel inference-time sampling.
We present a new inference-time sampler for diffusion models that gives a pretrained model a capability it was never trained for: constructing the atlas of the population it synthesizes. The sampler converges from every random seed to the population's central anatomy, which we ca...
ArXiv CS.CV
Source
Generated insight by OnAirToday AI
This breakthrough demonstrates that diffusion models implicitly encode underlying biological structures, allowing them to act as generative atlases without explicit anatomical training. By extracting these latent templates, researchers can significantly improve medical imaging workflows and diagnostic accuracy using existing AI frameworks.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.