Deep Learning Techniques for Inverse Problems in Imaging
arXiv:2005.06001
Abstract
Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging. We explore the central prevailing themes of this emerging area and present a taxonomy that can be used to categorize different problems and reconstruction methods. Our taxonomy is organized along two central axes: (1) whether or not a forward model is known and to what extent it is used in training and testing, and (2) whether or not the learning is supervised or unsupervised, i.e., whether or not the training relies on access to matched ground truth image and measurement pairs. We also discuss the trade-offs associated with these different reconstruction approaches, caveats and common failure modes, plus open problems and avenues for future work.
References in corpus (12)
- Generalized SURE for Exponential Families: Applications to Regularization
- Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
- One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
- Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
- Conditional density estimation in a regression setting
- Convolutional neural networks that teach microscopes how to image
- Learning to Invert: Signal Recovery via Deep Convolutional Networks
- Deep Optics for Monocular Depth Estimation and 3D Object Detection
- Global Guarantees for Blind Demodulation with Generative Priors
- Lower Bounds for Compressed Sensing with Generative Models
- Inverting Deep Generative models, One layer at a time
- Data-Driven Design for Fourier Ptychographic Microscopy