Career Fair and Career Events

Title: Computational Imaging: Reconciling Physical and Learned Models

Abstract: Computational imaging is a rapidly growing area that seeks to enhance the capabilities of imaging instruments by viewing imaging as an inverse problem. There are two traditionally distinct paradigms for designing computational imaging methods: model-based and learning-based. Model-based methods rely on analytical signal properties and often come with theoretical guarantees and insights.Learning-based methods use data-driven representations for best empirical performance through training on large datasets. This talk presents Regularization by ArtifactRemoval (RARE), as a framework for reconciling both viewpoints by providing a “deep learning” extension to the classical theory. RARE uses pre-trained“artifact-removing” deep neural nets for infusing a learned prior knowledge into the imaging problem, while maintaining a clear separation between the image prior and physics-based sensor model. Our results indicate that RARE can achieve state-of-the-art performance indifferent computational imaging tasks, while also being amenable to rigorous theoretical analysis. We will focus on the latest theoretical insights and applications of RARE in biomedical imaging, including MRI, CT, and optical microscopy.

Bio: Ulugbek S. Kamilov isAssistant Professor and Director of Computational Imaging Group (CIG) at WashingtonUniversity in St. Louis. He obtained the BSc/MSc degree in CommunicationSystems and the PhD degree in Electrical Engineering from EPFL, Switzerland, in2011 and 2015, respectively. From 2015 to 2017, he was a Research Scientist atMERL, Cambridge, MA, USA. He is a recipient of the NSF CAREER Award in 2021 and the IEEE Signal Processing Society’s 2017 Best Paper Award. He was among 55early-career researchers in the USA selected as a Fellow for the Scialog initiative on “Advancing Bioimaging" in 2021. His PhD thesis was selected asa finalist for the EPFL Doctorate Award in 2016. He has served as an AssociateEditor of IEEE Transactions on Computational Imaging (2019-present), BiologicalImaging (2020-present), and on IEEE Signal Processing Society’s ComputationalImaging Technical Committee (2016-2021). He was a plenary speaker at iTWIST 2018and is a program co-chair for BASP 2023. He has co-organized several large computational-imaging workshops, including IMA Special Workshop on Computational Imaging in 2019, Learning for Computational Imaging (LCI) Workshop at ICCV 2021, IEEE InternationalWorkshop on Computational Cameras and Displays (CCD) at CVPR 2022