Guided Variational Network for Image Decomposition
Cartoon-texture image decomposition is a critical preprocessing problem bottlenecked by the numerical intractability of classical variational or optimization models and the tedious manual tuning of global regularization parameters. We propose a Guided Variational Decomposition (GVD) model which introduces spatially adaptive quadratic norms whose pixelwise weights are learned either through local probabilistic statistics or via a lightweight neural network within a bilevel framework. This leads to a unified, interpretable, and computationally efficient model that bridges classical variational ideas with modern adaptive and data-driven methodologies. Numerical experiments on this framework, which inherently includes automatic parameter selection, delivers GVD as a robust, self-tuning, and superior solution for reliable image decomposition.
Authors
- Alessandro Lanza (ORCID: https://orcid.org/0000-0002-4904-0682)
- Serena Morigi (ORCID: https://orcid.org/0000-0001-8334-8798)
- Li Yang
- Youwei Wen (ORCID: https://orcid.org/0000-0002-9892-3668)
Institutions
- Hunan Normal University (CN)
- University of Bologna (IT)
Publication Details
- Journal
- SIAM Journal on Imaging Sciences
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1137/26m1841203
- Primary Topic
- Image and Signal Denoising Methods
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Istituto Nazionale di Alta Matematica "Francesco Severi"
- National Natural Science Foundation of China
- Gruppo Nazionale per il Calcolo Scientifico
- NextGenerationEU