Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution

arXiv:2604.12152v1 Announce Type: cross Abstract: Latent diffusion models for medical image super-resolution universally inherit variational autoencoders designed for natural photographs. We show that this default choice, not the diffusion architecture, is the dominant constraint on reconstruction quality. In a controlled experiment holding all other pipeline components fixed, replacing the generic Stable Diffusion VAE with MedVAE, a domain-specific autoencoder pretrained on more than 1.6 millio