SciFusion: Physics-Guided Compositional Diffusion for Multimodal 3D Scientific Image Generation
Read the original on arXiv Machine Learning →SciFusion is a multimodal framework that uses a latent diffusion backbone to generate unified 3D scientific images. It introduces a compositional conditioning scheme that separates each modality into domain, object, and contrast representations, allowing knowledge transfer and zero‑shot synthesis of unseen compositions. The model also incorporates physics‑informed objectives specific to MRI, CT, and electron microscopy to ensure generated images respect modality‑dependent image formation processes, and demonstrates improved fidelity and cross‑domain generalization across 15 imaging modalities.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.