Computational Imaging Group (CIG) is looking for motivated WashU students for the following summer research projects. If you are interested in a given project, please apply by emailing your resume to the project supervisor.

Blind Image Deblurring via Deep Learning

Status: reserved (Hou Lan) Description: Forming high-quality images of moving objects is an important problem in photography. The motion of the objects results in blur of an unknown shape that leads to the loss of resolution. Blind image deblurring seeks an algorithmic solution to this problem by jointly estimating the high-resolution image and the unknown. The goal of this project is to develop new blind image deblurring algorithms based on deep learning. Supervision: Ulugbek Kamilov (kamilov@wustl.edu) Areas: Image Restoration, Learning for Imaging

Fast and Stable Image Formation using Plug-In Operators

Status: reserved (Mingyang Xie) Description: Plug-In operators (such as ConvNets) are increasingly combined with traditional optimization algorithms for improving the quality of imaging. However, such combinations are typically ad hoc resulting in algorithms that are either unstable or slow. The goal of this project to overcome such limitations and develop an efficient plug-in algorithm for high-quality imaging. Supervision: Ulugbek Kamilov (kamilov@wustl.edu) Areas: Large-Scale Optimization, Image Restoration

Fast Algorithms for Computational Phase Retrieval

Status: reserved (Yiran Sun) Description: The recovery of an image given only the magnitude of its linear measurements is an important problem in computational microscopy. This problem arises due to the fact that optical acquisition devices do not generally allow for direct phase recording. Computational phase recovery seeks algorithmic solutions to this problem by combining statistical priors and optimization algorithms. The goal of this project is to develop novel fast phase recovery algorithms for quick and accurate computational phase retrieval. Supervision: Ulugbek Kamilov (kamilov@wustl.edu) Areas: Computational Microscopy, Large-Scale Optimization

Computational methods for quantitative brain MR imaging

Status: reserved (Max Torop and Ryogo Suzuki) Description: Quantitative magnetic resonance imaging (MRI) is a powerful tool for understanding the brain. However, reliable acquisition of high-quality MR images is difficult due to long scan times and patient motion. The goal of this project is to use machine learning to compensate for lost information in MR acquisition. The project is done in collaboration with WashU Medical School. In the context of this project, we are looking for 2 highly-motivated students comfortable coding and with interest in medical imaging. Supervision: Ulugbek Kamilov (kamilov@wustl.edu) Areas: Image Restoration, Learning for Imaging

Tradeoffs of Large-Scale Imaging

Status: reserved (Eric Tang) Description: Stochastic optimization algorithms (such as SGD) are increasingly popular for dealing with big datasets. However, exact tradeoffs between stochastic and batch algorithms is still not well understood. In this project, the goal is to investigate such tradeoffs in the context of large-scale imaging, where an image is reconstructed from a large number of measurements. This project is suitable for undergraduates interested in imaging research. Supervision: Ulugbek Kamilov (kamilov@wustl.edu) Areas: Large-Scale Optimization, Image Restoration

Next generation Cryo-EM imaging

Status: reserved (Shu Pan) Description: The Nobel Prize in Chemistry 2017 was awarded to the inventors of cryo-electron microscopy (Cryo-EM), which enables high-resolution imaging of biomolecules. Our goal is to improve cryo-EM by developing more advanced imaging algorithms that take into account sophisticated structural constraints. This project is performed in collaboration with Prof. Denis Fortun and might lead to opportunities to visit his group in France. The student is expected to have a good grasp of optimization and be comfortable coding in Matlab or Python. Supervision: Ulugbek Kamilov (kamilov@wustl.edu), Prof. Denis Fortun (CNRS, France) Areas: Computational Microscopy, Large-Scale Optimization

Deep Single-Molecule Super-Resolution Imaging

Status: active (Shiqi Xu) Description: The spatial resolution of traditional fluorescence microscopy techniques is limited by the diffraction of light. Super-resolution single-molecule microscopies such as STORM and PALM employ novel approaches to overcome the diffraction barriers, enabling biological studies at a nanometer scale. Recent works have shown that a convolutional neural network (CNN) could provide fast, accurate reconstructions for super-resolution imaging. The goal of this project is to develop a state-of-the-art deep learning based reconstruction method for single-molecule localization microscopy. Supervision: Yu Sun (sun.yu@wustl.edu), Ulugbek Kamilov Areas: Computational Microscopy, Learning for Imaging

Learning for material imaging with light

Status: active (Ray Wu) Description: Optical imaging has been widely applied in various fields such as material imaging for nano-chip design. Recent works have shown that deep neural networks (DNNs) are able to invert multiple light scattering and to reconstruct a high-quality two-dimensional (2D) image in a very short time, which is attractive for industrial applications. The goal of this project is to design a novel DNN architecture that can reconstruct 3D objects from the light measurements and deploy the model for material imaging. Supervision: Yu Sun (sun.yu@wustl.edu), Ulugbek Kamilov Areas: Computational Microscopy, Learning for Imaging

Learning for magnetic resonance imaging (MRI)

Status: active (Weijie Gan) Description: Magnetic resonance imaging (MRI) is a medical imaging technique used in radiology to form pictures of the anatomy and the physiological processes of the body. One of the key practical limitations of MRI is the long duration of data acquisition. The goal of this project is to reduce the scan times by using deep-learning-based imaging techniques. Supervision: Xiaojian Xu (xiaojianxu@wustl.edu), Ulugbek Kamilov Areas: Medical Imaging, Learning for Imaging

Regularization with ConvNets

Status: active (Jiaming Liu) Description: Convolutional neural networks (CNNs) have been successfully applied to numerous tasks in computational imaging and computer vision. Currently, their application for regularization of ill-posed inverse problems is a popular topic of research. In this project, the goal is to investigate various strategies of incorporating CNNs for stabilizing image reconstruction with applications to optical imaging. Supervision: Yu Sun (sun.yu@wustl.edu), Ulugbek Kamilov Areas: Learning for Imaging, Medical Imaging

• Regularization with ConvNets (J. Liu, Y. Sun, U. S. Kamilov)
• Learning for 3D computational imaging (W. Gan, X. Xu, U. S. Kamilov)
• Convolutional dictionary learning for image reconstruction (F. Long, X. Xu, U. S. Kamilov)
• Unsupervised deep image learning (H. Zou, Y. Sun, U. S. Kamilov)
• Distributed algorithms for nonconvex stochastic optimization (M. Abijaoude, U. S. Kamilov)
• Learning for material imaging with light (R. Wu, Y. Sun, U. S. Kamilov)
• Image restoration with GANs (F. Zhai, Y. Sun, U. S. Kamilov)
• Learning for MRI (J. Xing, X. Xu, U. S. Kamilov)
• Learning for material imaging with light (R. Wu, Y. Sun, U. S. Kamilov)
• Dictionary Learning for Fourier Ptychographic Microscopy (S. Xu, X. Xu, U. S. Kamilov)