Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior
This work addresses a computational bottleneck for researchers in inverse imaging problems, offering a more efficient method for posterior estimation, though it is incremental as it builds on existing score-based priors.
The authors tackled the computational inefficiency of using score-based diffusion models as priors in Bayesian imaging by proposing a surrogate prior based on the evidence lower bound, which accelerates variational inference by at least two orders of magnitude and improves posterior estimation accuracy compared to non-variational methods.
We propose a surrogate function for efficient yet principled use of score-based priors in Bayesian imaging. We consider ill-posed inverse imaging problems in which one aims for a clean image posterior given incomplete or noisy measurements. Since the measurements do not uniquely determine a true image, a prior is needed to constrain the solution space. Recent work turned score-based diffusion models into principled priors for solving ill-posed imaging problems by appealing to an ODE-based log-probability function. However, evaluating the ODE is computationally inefficient and inhibits posterior estimation of high-dimensional images. Our proposed surrogate prior is based on the evidence lower bound of a score-based diffusion model. We demonstrate the surrogate prior on variational inference for efficient approximate posterior sampling of large images. Compared to the exact prior in previous work, our surrogate accelerates optimization of the variational image distribution by at least two orders of magnitude. We also find that our principled approach gives more accurate posterior estimation than non-variational diffusion-based approaches that involve hyperparameter-tuning at inference. Our work establishes a practical path forward for using score-based diffusion models as general-purpose image priors.