Learning Regularization Functionals for Inverse Problems: A Comparative Study
By: Johannes Hertrich , Hok Shing Wong , Alexander Denker and more
Potential Business Impact:
Makes computer images clearer and sharper.
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.
Similar Papers
Introduction to Regularization and Learning Methods for Inverse Problems
Numerical Analysis
Teaches computers to solve tricky puzzles from incomplete clues.
Data-driven approaches to inverse problems
Numerical Analysis
Lets computers see inside things using smart guessing.
Self-supervised learning for phase retrieval
Information Retrieval
Fixes blurry medical pictures without needing perfect copies.