Bilevel parameter learning for higher-order total variation regularisation models

Abstract

We consider a bilevel optimisation approach for parameter learning in higher-order total variation image reconstruction models. Apart from the least squares cost functional, naturally used in bilevel learning, we propose and analyse an alternative cost, based on a Huber regularised TV-seminorm. Differentiability properties of the solution operator are verified and a first-order optimality system is derived. Based on the adjoint information, a quasi-Newton algorithm is proposed for the numerical solution of the bilevel problems. Numerical experiments are carried out to show the suitability of our approach and the improved performance of the new cost functional. Thanks to the bilevel optimisation framework, also a detailed comparison between TGV${}^2$ and ICTV is carried out, showing the advantages and shortcomings of both regularisers, depending on the structure of the processed images and their noise level.

References in corpus (1)

• The structure of optimal parameters for image restoration problems

Cited by in corpus (20)

• Solving ill-posed inverse problems using iterative deep neural networks
• Higher-order total variation approaches and generalisations
• Core Imaging Library -- Part II: Multichannel reconstruction for dynamic and spectral tomography
• A Bilevel Approach for Parameter Learning in Inverse Problems
• Bilevel parameter learning for nonlocal image denoising models
• Analysis and optimisation of a variational model for mixed Gaussian and Salt & Pepper noise removal
• Dualization and Automatic Distributed Parameter Selection of Total Generalized Variation via Bilevel Optimization
• Inertial, corrected, primal-dual proximal splitting
• Acceleration of the PDHGM on strongly convex subspaces
• Joint super-resolution image reconstruction and parameter identification in imaging operator: Analysis of bilinear operator equations, numerical solution, and application to magnetic particle imaging
• Linearly convergent bilevel optimization with single-step inner methods
• Bilevel training schemes in imaging for total-variation-type functionals with convex integrands
• Discrete Total Variation of the Normal Vector Field as Shape Prior with Applications in Geometric Inverse Problems
• Regularization Graphs -- A unified framework for variational regularization of inverse problems
• Dyadic partition-based training schemes for TV/TGV denoising
• Bilevel Inverse Problems in Neuromorphic Imaging
• Diffusion tensor imaging with deterministic error bounds
• Regularization of Inverse Problems: Deep Equilibrium Models versus Bilevel Learning
• Enhanced hyperspectral tomography for bioimaging by spatiospectral reconstruction
• Dual-grid parameter choice method with application to image deblurring