Michael T. McCann
YOU?
Author Swipe
View article: Deep Parameter Interpolation for Scalar Conditioning
Deep Parameter Interpolation for Scalar Conditioning Open
We propose deep parameter interpolation (DPI), a general-purpose method for transforming an existing deep neural network architecture into one that accepts an additional scalar input. Recent deep generative models, including diffusion mode…
View article: 138 Complex Care Needs of Congestive Heart Failure Patients Presenting to the Emergency Department
138 Complex Care Needs of Congestive Heart Failure Patients Presenting to the Emergency Department Open
View article: 333 Educational Impact of a Dedicated Emergency Medicine Teaching Attending Shift
333 Educational Impact of a Dedicated Emergency Medicine Teaching Attending Shift Open
View article: In situ damage and deformation of Allende meteorite and tuff materials during synchrotron based high-speed 3D tomography.
In situ damage and deformation of Allende meteorite and tuff materials during synchrotron based high-speed 3D tomography. Open
View article: Plug-and-Play Priors as a Score-Based Method
Plug-and-Play Priors as a Score-Based Method Open
Plug-and-play (PnP) methods are extensively used for solving imaging inverse problems by integrating physical measurement models with pre-trained deep denoisers as priors. Score-based diffusion models (SBMs) have recently emerged as a powe…
View article: Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models
Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models Open
We present a concise derivation for several influential score-based diffusion models that relies on only a few textbook results. Diffusion models have recently emerged as powerful tools for generating realistic, synthetic signals -- partic…
View article: Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction
Swap-Net: A Memory-Efficient 2.5D Network for Sparse-View 3D Cone Beam CT Reconstruction Open
Reconstructing 3D cone beam computed tomography (CBCT) images from a limited set of projections is an important inverse problem in many imaging applications from medicine to inertial confinement fusion (ICF). The performance of traditional…
View article: Isotopic gamma lines for identification of shielding materials
Isotopic gamma lines for identification of shielding materials Open
Identifying the constituting materials of concealed objects is crucial in a wide range of sectors, such as medical imaging, geophysics, nonproliferation, national security investigations, and so on. Existing methods face limitations, parti…
View article: Learning from Hydrodynamics Simulations with Mass Constraints for Density Reconstruction in Dynamic Tomography
Learning from Hydrodynamics Simulations with Mass Constraints for Density Reconstruction in Dynamic Tomography Open
View article: High Fidelity Tomographic Density Reconstructions
High Fidelity Tomographic Density Reconstructions Open
View article: Dynamic Imaging: Beyond the Standard Model
Dynamic Imaging: Beyond the Standard Model Open
View article: Supervised Reconstruction for Silhouette Tomography
Supervised Reconstruction for Silhouette Tomography Open
In this paper, we introduce silhouette tomography, a novel formulation of X-ray computed tomography that relies only on the geometry of the imaging system. We formulate silhouette tomography mathematically and provide a simple method for o…
View article: Supervised Reconstruction for Silhouette Tomography
Supervised Reconstruction for Silhouette Tomography Open
In this paper, we introduce silhouette tomography, a novel formulation of X-ray computed tomography that relies only on the geometry of the imaging system. We formulate silhouette tomography mathematically and provide a simple method for o…
View article: Robust and Simple ADMM Penalty Parameter Selection
Robust and Simple ADMM Penalty Parameter Selection Open
We present a new method for online selection of the penalty parameter for the alternating direction method of multipliers (ADMM) algorithm. ADMM is a widely used method for solving a range of optimization problems, including those that ari…
View article: PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction Open
Ptychography is an imaging technique that captures multiple overlapping snapshots of a sample, illuminated coherently by a moving localized probe. The image recovery from ptychographic data is generally achieved via an iterative algorithm …
View article: Isotopic gamma lines for identification of shielding materials
Isotopic gamma lines for identification of shielding materials Open
Identifying the constituting materials of concealed objects is crucial in a wide range of sectors, such as medical imaging, geophysics, nonproliferation, national security investigations, and so on. Existing methods face limitations, parti…
View article: PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction
PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstruction Open
Ptychography is an imaging technique that captures multiple overlapping snapshots of a sample, illuminated coherently by a moving localized probe. The image recovery from ptychographic data is generally achieved via an iterative algorithm …
View article: Model-Based Reconstruction with Learning: From Unsupervised to Supervised and Beyond
Model-Based Reconstruction with Learning: From Unsupervised to Supervised and Beyond Open
Many techniques have been proposed for image reconstruction in medical imaging that aim to recover high-quality images especially from limited or corrupted measurements. Model-based reconstruction methods have been particularly popular (e.…
View article: Comparison of Supervised and Un-Supervised Machine Learning Algorithms for Threat Detection and Scintillator Performance for Radiation Portal Monitoring
Comparison of Supervised and Un-Supervised Machine Learning Algorithms for Threat Detection and Scintillator Performance for Radiation Portal Monitoring Open
Following the events of September 11, 2001, international border crossing have been equipped with radiation portal monitors (RPMs) to identify illicit radioactive material. Polyvinyl toluene (PVT) scintillators are commonly used due to the…
View article: Score-based Diffusion Models for Bayesian Image Reconstruction
Score-based Diffusion Models for Bayesian Image Reconstruction Open
This paper explores the use of score-based diffusion models for Bayesian image reconstruction. Diffusion models are an efficient tool for generative modeling. Diffusion models can also be used for solving image reconstruction problems. We …
View article: Material Identification From Radiographs Without Energy Resolution
Material Identification From Radiographs Without Energy Resolution Open
We propose a method for performing material identification from radiographs without energy-resolved measurements. Material identification has a wide variety of applications, including in biomedical imaging, nondestructive testing, and secu…
View article: Material Identification From Radiographs Without Energy Resolution
Material Identification From Radiographs Without Energy Resolution Open
We propose a method for performing material identification from radiographs without energy-resolved measurements. Material identification has a wide variety of applications, including in biomedical imaging, nondestructive testing, and secu…
View article: Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models Open
Diffusion models have emerged as the new state-of-the-art generative model with high quality samples, with intriguing properties such as mode coverage and high flexibility. They have also been shown to be effective inverse problem solvers,…
View article: Scientific Computational Imaging Code (SCICO)
Scientific Computational Imaging Code (SCICO) Open
Scientific Computational Imaging Code (SCICO) is a Python package for solving the inverse problems that arise in scientific imaging applications. Its primary focus is providing methods for solving ill-posed inverse problems by using an app…
View article: Comparing one-step and two-step scatter correction and density reconstruction in x-ray CT
Comparing one-step and two-step scatter correction and density reconstruction in x-ray CT Open
In this work, we compare one-step and two-step approaches for X-ray computed tomography (CT) scatter correction and density reconstruction. X-ray CT is an important imaging technique in medical and industrial applications. In many cases, t…
View article: Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion Posterior Sampling for General Noisy Inverse Problems Open
Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linea…
View article: Learning Sparsity-Promoting Regularizers using Bilevel Optimization
Learning Sparsity-Promoting Regularizers using Bilevel Optimization Open
We present a method for supervised learning of sparsity-promoting regularizers for denoising signals and images. Sparsity-promoting regularization is a key ingredient in solving modern signal reconstruction problems; however, the operators…
View article: High-precision inversion of dynamic radiography using hydrodynamic features
High-precision inversion of dynamic radiography using hydrodynamic features Open
While radiography is routinely used to probe complex, evolving density fields in research areas ranging from materials science to shock physics to inertial confinement fusion and other national security applications, complications resultin…
View article: Bilevel learning of l1-regularizers with closed-form gradients(BLORC)
Bilevel learning of l1-regularizers with closed-form gradients(BLORC) Open
We present a method for supervised learning of sparsity-promoting regularizers, a key ingredient in many modern signal reconstruction problems. The parameters of the regularizer are learned to minimize the mean squared error of reconstruct…
View article: Comparing One-step and Two-step Scatter Correction and Density Reconstruction in X-ray CT
Comparing One-step and Two-step Scatter Correction and Density Reconstruction in X-ray CT Open
In this work, we compare one-step and two-step approaches for X-ray computed tomography (CT) scatter correction and density reconstruction. X-ray CT is an important imaging technique in medical and industrial applications. In many cases, t…