Generative Translation Priors: Bayesian Imaging with Cross-Modality Image Translation
This work introduces Generative Translation Priors--a Bayesian framework that transforms diffusion-based image-to-image translation models into cross-modality image priors for ill-posed imaging inverse problems, and derives two discretized GTP algorithms based on gradient and proximal likelihood guidance.
Evan Bell, Jiaming Liu, Yifan Chen et al.
· 0 citations