Abstract
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 call the \emph{intrinsic atlas}. The advantage is threefold. (1) It requires no retraining. A diffusion model that has already learned a coherent population, including the released ones, yields its atlas in a single inference pass without involving deformable registration. (2) It applies to multiple domains, such as brain MRI, chest X-ray, faces, and 3D shapes. (3) It extends to subpopulations. One age-conditioned model gives an atlas at any age in its training range, and the resulting family reproduces the CSF expansion of healthy aging. Evaluated as a registration target, the intrinsic atlas is best or second-best on every dataset against classical and learned templates, and the most central template on held-out brain MRI cohorts. Atlas construction can be reframed as a byproduct of generative modeling: a diffusion model is a learned representation of population structure, and the atlas is what it already contains.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Shi, J., Femiani, J., & Wonka, P. (2026). Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models. https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models
MLA 9
Shi, Jian, et al. "Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models." https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models.
Chicago (author–date)
Shi, Jian, John Femiani, and Peter Wonka. 2026. "Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models." https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models.
Harvard
Shi, J., Femiani, J. and Wonka, P. (2026) 'Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models', Available at: https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models.
Vancouver
Shi J, Femiani J, Wonka P. Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models. https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models
IEEE
J. Shi, J. Femiani, and P. Wonka, "Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models," https://omanscience.com/en/articles/atlases-are-already-inside-recovering-population-templates-from-pretrained-diffusion-models.