
JS
Jian Shi, John Femiani, Peter Wonka
· 1 min read
ResearcharXiv cs.CV
Atlases Are Already Inside: Recovering Population Templates from Pretrained Diffusion Models
arXiv:2609.30566v1 Announce Type: new
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.
Original source
This story was published by arXiv cs.CV and written by Jian Shi, John Femiani, Peter Wonka. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


