Computational Imaging Group (CIG) at Washington University in St. Louis pursues research on the development of advanced algorithms and theoretical foundations for processing and analyzing spatiotemporal data. Topics of interest include the acquisition, reconstruction, and analysis of visual and imaging data. Research effort is taking place at two complementary levels:
- Fundamental and mathematical aspects of imaging
- Application-oriented projects in collaboration with our partners
Some of our recent research is summarized below. We also maintain a separate list of research projects available to current WashU undergraduate or graduate students.
||Much of modern biomedical imaging is based on linear models that assume that photons travel following a straight path. This makes corresponding imaging methods inaccurate for many applications by placing fundamental limits—in terms of resolution, penetration, and quality. Our goal is to build methods for imaging under nonlinear scattering scenarios.
||CIG collaborates with researchers at Washington University School of Medicine on imaging algorithms for enabling better and early diagnosis, and increased patient comfort. Some of our most exciting projects are in the area of magnetic resonance imaging (MRI), where our ultimate goal is be able to efficiently process large-datasets for detecting information useful to healthcare professionals.
Deep Learning for Imaging
||Imaging data exhibits intricate relationships, spatiotemporal dependencies, and nontrivial features. However, finding automatic ways to exploiting such dependencies in practice is difficult. CIG specializes in the development of mathematically rigorous methods integrating state-of-the-art deep learning into scalable imaging algorithms with provable guarantees.
||Can information lost during data acquisition be algorithmically recovered? Information loss is inevitable due to practical hardware and acquisition constraints. CIG develops technology for the recovery of lost information using advanced computational algorithms powered by machine learning. Our research considers the complete imaging pipeline from sensing all the way to analysis to guide the design of compressive imaging technology.
- Dr. Emrah Bostan, UC Berkeley, Berkeley, USA
- Dr. Petros Boufounos, MERL, Cambridge, USA
- Prof. Alyson Fletcher, UCLA, Los Angeles, USA
- Prof. Vivek Goyal, Boston University, Boston, USA
- Dr. Dehong Liu, MERL, Cambridge, USA
- Dr. Hassan Mansour, MERL, Cambridge, USA
- Prof. Demetri Psaltis, EPFL, Lausanne, Switzerland
- Prof. Sundeep Rangan, New York University, New York, USA
- Prof. Philip Schniter, Ohio State University, Columbus, USA
- Prof. Lei Tian, Boston University, Boston, USA
- Prof. Michael Unser, EPFL, Lausanne, Switzerland
- Dr. Anthony Vetro, MERL, Cambridge, USA
- Prof. Laura Waller, UC Berkeley, Berkeley, USA
- Dr. Brendt Wohlberg, Los Alamos National Laboratory, Los Alamos, USA