Diffusion posterior sampling for general noisy inverse problems

H Chung, J Kim, MT Mccann, ML Klasky… - arxiv preprint arxiv …, 2022 - arxiv.org
Diffusion models have been recently studied as powerful generative inverse problem
solvers, owing to their high quality reconstructions and the ease of combining existing …

Plug-and-play methods for integrating physical and learned models in computational imaging: Theory, algorithms, and applications

US Kamilov, CA Bouman, GT Buzzard… - IEEE Signal …, 2023 - ieeexplore.ieee.org
Plug-and-play (PnP) priors constitute one of the most widely used frameworks for solving
computational imaging problems through the integration of physical models and learned …

Direct diffusion bridge using data consistency for inverse problems

H Chung, J Kim, JC Ye - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Diffusion model-based inverse problem solvers have shown impressive performance, but
are limited in speed, mostly as they require reverse diffusion sampling starting from noise …

Prompt-tuning latent diffusion models for inverse problems

H Chung, JC Ye, P Milanfar, M Delbracio - arxiv preprint arxiv:2310.01110, 2023 - arxiv.org
We propose a new method for solving imaging inverse problems using text-to-image latent
diffusion models as general priors. Existing methods using latent diffusion models for …

What's in a Prior? Learned Proximal Networks for Inverse Problems

Z Fang, S Buchanan, J Sulam - arxiv preprint arxiv:2310.14344, 2023 - arxiv.org
Proximal operators are ubiquitous in inverse problems, commonly appearing as part of
algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep …

Video Super-Resolution Using Plug-and-Play Priors

MC Zerva, LP Kondi - IEEE Access, 2024 - ieeexplore.ieee.org
Video super-resolution is a fundamental task in computer vision, aiming to enhance the
resolution and visual quality of low-resolution videos. Plug-and-Play Priors is one of the …

Efficient compressed sensing reconstruction for 3D fluorescence microscopy using OptoMechanical Modulation Tomography (OMMT) with a 1+ 2D regularization

F Marelli, M Liebling - Optics Express, 2023 - opg.optica.org
OptoMechanical Modulation Tomography (OMMT) exploits compressed sensing to
reconstruct high resolution microscopy volumes from fewer measurement images compared …

[HTML][HTML] Using an Improved Regularization Method and Rigid Transformation for Super-Resolution Applied to MRI Data

MC Zerva, G Chantas, LP Kondi - Information, 2024 - mdpi.com
Super-resolution (SR) techniques have shown significant promise in enhancing the
resolution of MRI images, which are often limited by hardware constraints and acquisition …

Trinidi: Time-of-flight resonance imaging with neutrons for isotopic density inference

T Balke, AM Long, SC Vogel… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Accurate reconstruction of 2D and 3D isotope densities is a desired capability with great
potential impact in applications such as evaluation and development of next-generation …

Closed-Form Approximation of the Total Variation Proximal Operator

EP Chandler, S Shoushtari, B Wohlberg… - arxiv preprint arxiv …, 2024 - arxiv.org
Total variation (TV) is a widely used function for regularizing imaging inverse problems that
is particularly appropriate for images whose underlying structure is piecewise constant. TV …