2025/03/11 by Gexin Huang, Huang, Gexin, Zhangsihao Yang +9 · 1 voice · 1 citation
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Graphics (cs.GR) #cs.GR
paper · pdf · doi:10.48550/arxiv.2503.09634
openalex publication_date 2025/03/11 · arxiv published 2025/03/11 · arxiv updated 2025/03/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Structural and appearance changes in brain imaging over time are crucial indicators of neurodevelopment and neurodegeneration. The rapid advancement of large-scale generative models provides a promising backbone for modeling these complex global and local changes in brain images, such as transforming the age of a source image to a target age. However, current generative models, typically trained on independently and identically distributed (i.i.d.) data, may struggle to maintain intra-subject spatiotemporal consistency during transformations. We propose the Identity-Preserving Longitudinal Diffusion Model (IP-LDM), designed to accurately transform brain ages while preserving subject identity. Our approach involves first extracting the identity representation from the source image. Then, conditioned on the target age, the latent diffusion model learns to generate the age-transformed target image. To ensure consistency within the same subject over time, we regularize the identity representation using a triplet contrastive formulation. Our experiments on both elderly and infant brain datasets demonstrate that our model outperforms existing conditional generative models, producing realistic age transformations while preserving intra-subject identity.