Author:
Duff M. A. G.,Campbell N. D. F.,Ehrhardt M. J.
Abstract
AbstractDeep neural network approaches to inverse imaging problems have produced impressive results in the last few years. In this survey paper, we consider the use of generative models in a variational regularisation approach to inverse problems. The considered regularisers penalise images that are far from the range of a generative model that has learned to produce images similar to a training dataset. We name this family generative regularisers. The success of generative regularisers depends on the quality of the generative model and so we propose a set of desired criteria to assess generative models and guide future research. In our numerical experiments, we evaluate three common generative models, autoencoders, variational autoencoders and generative adversarial networks, against our desired criteria. We also test three different generative regularisers on the inverse problems of deblurring, deconvolution, and tomography. We show that restricting solutions of the inverse problem to lie exactly in the range of a generative model can give good results but that allowing small deviations from the range of the generator produces more consistent results. Finally, we discuss future directions and open problems in the field.
Funder
Engineering and Physical Sciences Research Council
Royal Society
Leverhulme Trust
Publisher
Springer Science and Business Media LLC
Subject
Applied Mathematics,Geometry and Topology,Computer Vision and Pattern Recognition,Condensed Matter Physics,Modeling and Simulation,Statistics and Probability
Reference90 articles.
1. Scherzer, O., Grasmair, M., Grossauer, H., Haltmeier, M., Lenzen, F.: Variational regularization methods for the solution of inverse problems. In: Variational Methods in Imaging (2019)
2. Applied Mathematics;K Ito,2014
3. Benning, M., Burger, M.: Modern regularization methods for inverse problems. Acta Numer. 27, 1–111 (2018)
4. Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D 60, 259–268 (1992)
5. Aharon, M., Elad, M., Bruckstein, A.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54, 4311–4322 (2006)
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Iteratively Refined Image Reconstruction with Learned Attentive Regularizers;Numerical Functional Analysis and Optimization;2024-07-03
2. Joint PET/CT Reconstruction Using a Double Variational Autoencoder;2023 IEEE Nuclear Science Symposium, Medical Imaging Conference and International Symposium on Room-Temperature Semiconductor Detectors (NSS MIC RTSD);2023-11-04