Learning Regularization Functionals for Inverse Problems: A Comparative Study
This work addresses a gap for researchers in computational imaging by facilitating direct comparisons of existing methods, though it is incremental as it does not introduce new techniques.
The authors tackled the challenge of comparing diverse learned regularization methods for imaging inverse problems by unifying available code into a common framework, enabling systematic analysis and practical guidelines.
In recent years, a variety of learned regularization frameworks for solving inverse problems in imaging have emerged. These offer flexible modeling together with mathematical insights. The proposed methods differ in their architectural design and training strategies, making direct comparison challenging due to non-modular implementations. We address this gap by collecting and unifying the available code into a common framework. This unified view allows us to systematically compare the approaches and highlight their strengths and limitations, providing valuable insights into their future potential. We also provide concise descriptions of each method, complemented by practical guidelines.