Deep unfolding of a proximal interior point method for image restoration

• Published in: Inverse problems Vol. 36; no. 3; pp. 34005 - 34031
• Main Authors: Bertocchi, C, Chouzenoux, E, Corbineau, M-C, Pesquet, J-C, Prato, M
• Format: Journal Article
• Language: English
• Published: IOP Publishing 01.03.2020
• Subjects: Computer Science; deep unfolding; Image Processing; image restoration; interior point method; Machine Learning; Mathematics; neural network; Optimization and Control; proximal algorithms; regularization; deep unfolding; proximal algorithms; image restoration; Neural networks; regularization; Interior point method; Interior point methods; neural network
• ISSN: 0266-5611; 1361-6420
• DOI: 10.1088/1361-6420/ab460a

Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters, which can be estimated through computationally expensive and time-consuming methods. In contrast, deep learning offers very generic and efficient architectures, at the expense of explainability, since it is often used as a black-box, without any fine control over its output. Deep unfolding provides a convenient approach to combine variational-based and deep learning approaches. Starting from a variational formulation for image restoration, we develop iRestNet, a neural network architecture obtained by unfolding a proximal interior point algorithm. Hard constraints, encoding desirable properties for the restored image, are incorporated into the network thanks to a logarithmic barrier, while the barrier parameter, the stepsize, and the penalization weight are learned by the network. We derive explicit expressions for the gradient of the proximity operator for various choices of constraints, which allows training iRestNet with gradient descent and backpropagation. In addition, we provide theoretical results regarding the stability of the network for a common inverse problem example. Numerical experiments on image deblurring problems show that the proposed approach compares favorably with both state-of-the-art variational and machine learning methods in terms of image quality.