Learned Reconstruction Methods

Learned Reconstruction Methods. Deep image priors and unrolled networks for inverse problems.

Recent technical contributions

A handful of recent papers carry the methodological frontier of learned reconstruction methods forward. Solving inverse problems using data-driven models (Arridge et al., 2019) is a primary reference for this area and develops new techniques or results that downstream work builds on. Deep learning techniques for inverse problems in imaging (Ongie et al., 2020) pushes the technical state of the art and is widely cited in subsequent work on the topic.

Open methodological questions for learned reconstruction methods include sharpening the bridges between foundational theory and computational practice, extending classical results to broader or more structured settings, and integrating the techniques surveyed above with adjacent mathematical disciplines. The references listed in this page are the entry points that current work builds on.