6 papers
NullFlow: One-Step Generative Reconstruction
Xiao Shi, Edward P. Chandler, Chicago Y. Park +2
We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measurement-consistent subspace. Becau…
Stochastic Generative Plug-and-Play Priors
Chicago Y. Park, Edward P. Chandler, Yuyang Hu +4
Plug-and-play (PnP) methods are widely used for solving imaging inverse problems by incorporating a denoiser into optimization algorithms. Score-based diffusion models (SBDMs) have…
Moments Matter: Posterior Recovery in Poisson Denoising via Log-Networks
Shirin Shoushtari, Edward P. Chandler, Ulugbek S. Kamilov
Poisson denoising plays a central role in photon-limited imaging applications such as microscopy, astronomy, and medical imaging. It is common to train deep learning models for den…
Analysis Plug-and-Play Methods for Imaging Inverse Problems
Edward P. Chandler, Shirin Shoushtari, Brendt Wohlberg +1
Plug-and-Play Priors (PnP) is a popular framework for solving imaging inverse problems by integrating learned priors in the form of denoisers trained to remove Gaussian noise from…
Closed-Form Approximation of the Total Variation Proximal Operator
Edward P. Chandler, Shirin Shoushtari, Brendt Wohlberg +1
Total variation (TV) is a widely used function for regularizing imaging inverse problems that is particularly appropriate for images whose underlying structure is piecewise constan…
Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Models
Shirin Shoushtari, Edward P. Chandler, Yuanhao Wang +2
Diffusion models are widely used as priors in imaging inverse problems. However, their performance often degrades under distribution shifts between the training and test-time image…