Variational Inference for Computational Imaging Inverse Problems
This work addresses the problem of high data collection costs in computational imaging for researchers and practitioners, offering a practical solution that is incremental in combining existing methods.
The paper tackles the challenge of training Bayesian models for computational imaging with minimal data by introducing a framework that combines few experimental data, domain expertise, and existing datasets, achieving state-of-the-art reconstructions in holographic imaging and imaging through scattering media with little training data.
Machine learning methods for computational imaging require uncertainty estimation to be reliable in real settings. While Bayesian models offer a computationally tractable way of recovering uncertainty, they need large data volumes to be trained, which in imaging applications implicates prohibitively expensive collections with specific imaging instruments. This paper introduces a novel framework to train variational inference for inverse problems exploiting in combination few experimentally collected data, domain expertise and existing image data sets. In such a way, Bayesian machine learning models can solve imaging inverse problems with minimal data collection efforts. Extensive simulated experiments show the advantages of the proposed framework. The approach is then applied to two real experimental optics settings: holographic image reconstruction and imaging through highly scattering media. In both settings, state of the art reconstructions are achieved with little collection of training data.