Latent Score-Based Bayesian Cramér-Rao Bound Estimation for High-Dimensional Imaging Systems

License: See LICENSE file · Updated 2026-10-06
My rating

The paper addresses Bayesian Cramér-Rao bound estimation for high-dimensional imaging inverse problems with complex priors that are difficult to model analytically. Its framework reformulates the inverse problem in the latent space of a pre-trained model, targeting the estimation of prior scores and the construction and inversion of high-dimensional Bayesian Fisher information matrices. The work falls within scientific machine learning for computational imaging and inverse-problem analysis.

Tags: