Variational Inference for Computational Imaging Inverse Problems
arXiv:1904.06264
Abstract
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.
arXiv comment29+15 Pages
References in corpus (15)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Generative Adversarial Text to Image Synthesis
- Conditional Image Synthesis With Auxiliary Classifier GANs
- Phase recovery and holographic image reconstruction using deep learning in neural networks
- Compressed Sensing using Generative Models
- Auxiliary Deep Generative Models
- Image Transformer
- Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
- Recurrent Inference Machines for Solving Inverse Problems
- Deep Bayesian Inversion
- One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
- Holographic Phase Retrieval and Reference Design
- Hybrid Models with Deep and Invertible Features
- Probabilistic Residual Learning for Aleatoric Uncertainty in Image Restoration