Using Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods

By Alice Lucas, Michael Iliadis, Rafael Molina, Aggelos K. Katsaggelos. 2018

520 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Radiation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Radiation

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “(30)See [154, 155, 156, 157, 158] for recent perspectives and developments connecting deep learning-based reconstruction methods to the more general research field of inverse problems.”
Snapshot Compressive Imaging: Theory, Algorithms, and Applications (2021, background): “Equation (24) is usually solved by iterative algorithms, and various solvers exist based on different forms of ( ) x R [44].”
Deep speckle correlation: a deep learning approach toward scalable imaging through scattering media (2018, background): “DL is proven to be extremely powerful in solving complex imaging problems, providing performance surpassing those using state-of-the-art model-based techniques [34], such as super-resolution [43, 57], deconvolution [58, 61], compressive imaging [27, 60], tomography [19], holography [42,44], and phas”
Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing (2019, background): “An excellent tutorial article covering these issues is [12].”
Deep Learning Techniques for Inverse Problems in Imaging (2020, background): “In the last five years deep learning has demonstrated enormous potential for solving a host of imaging inverse problems; see [26].”
Artificial intelligence in the creative industries: a review (2020, background): “e divide restoration into four classes that relate to work in the creative industries with examples illustrated in Fig. 7. Further details of deep learning for inverse problem solving can be found in [261]. i) Deblurring: Images can be distorted by blur, due to poor camera focus or camera or subject”
Deep Learning on Image Denoising: An overview (2019, unknown): “Although most of the above methods have achieved reasonably good performance in image denoising, they suffered from several drawbacks [146], including the need for optimization meth-ods for the test phase, manual setting parameters, and a certain model for single denoising tasks.”
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models (2021, background): “Finally, there is signiﬁcant prior work on deep learning meth-ods that do not rely on pre-trained generators, see e.g. (Lucas et al., 2018; Yu et al., 2019; Liu et al., 2019; Sun & Chen, 2020; Sun et al., 2020; Yang et al., 2019; Tian et al., 2020; Tripathi et al., 2018).”
On instabilities of deep learning in image reconstruction and the potential costs of AI (2019, background): “Artificial intelligence (AI) techniques such as deep learning and neural networks [4] have provided a new paradigm with new techniques in inverse problems that may change the field [5], [6], [7], [8], [9], [10], [11], [12].”
Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk (2017, background): “See [44] for a review of deep learning for inverse problems in imaging.”