Steerable conditional diffusion for out-of-distribution adaptation in imaging inverse problems

R Barbano, A Denker, H Chung, TH Roh… - arxiv preprint arxiv …, 2023 - arxiv.org
Denoising diffusion models have emerged as the go-to framework for solving inverse
problems in imaging. A critical concern regarding these models is their performance on out …

Score-based generative models for PET image reconstruction

IRD Singh, A Denker, R Barbano, Ž Kereta… - arxiv preprint arxiv …, 2023 - arxiv.org
Score-based generative models have demonstrated highly promising results for medical
image reconstruction tasks in magnetic resonance imaging or computed tomography …

AmbientFlow: Invertible generative models from incomplete, noisy measurements

VA Kelkar, R Deshpande, A Banerjee… - arxiv preprint arxiv …, 2023 - arxiv.org
Generative models have gained popularity for their potential applications in imaging
science, such as image reconstruction, posterior sampling and data sharing. Flow-based …

Missing wedge completion via unsupervised learning with coordinate networks

D Van Veen, JG Galaz-Montoya, L Shen… - International Journal of …, 2024 - mdpi.com
Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling
detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its …

Conditional score-based diffusion models for solving inverse problems in mechanics

A Dasgupta, H Ramaswamy, J Murgoitio-Esandi… - arxiv preprint arxiv …, 2024 - arxiv.org
We propose a framework to perform Bayesian inference using conditional score-based
diffusion models to solve a class of inverse problems in mechanics involving the inference of …

Benchmarking learned algorithms for computed tomography image reconstruction tasks

MB Kiss, A Biguri, Z Shumaylov, F Sherry… - arxiv preprint arxiv …, 2024 - arxiv.org
Computed tomography (CT) is a widely used non-invasive diagnostic method in various
fields, and recent advances in deep learning have led to significant progress in CT image …

Provably convergent data-driven convex-nonconvex regularization

Z Shumaylov, J Budd, S Mukherjee… - arxiv preprint arxiv …, 2023 - arxiv.org
An emerging new paradigm for solving inverse problems is via the use of deep learning to
learn a regularizer from data. This leads to high-quality results, but often at the cost of …

Conditional score-based diffusion models for solving inverse elasticity problems

A Dasgupta, H Ramaswamy, J Murgoitio-Esandi… - Computer Methods in …, 2025 - Elsevier
We propose a framework to perform Bayesian inference using conditional score-based
diffusion models to solve a class of inverse problems in mechanics involving the inference of …

Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation

Z Shumaylov, J Budd, S Mukherjee… - arxiv preprint arxiv …, 2024 - arxiv.org
Variational regularisation is the primary method for solving inverse problems, and recently
there has been considerable work leveraging deeply learned regularisation for enhanced …

Conditional score-based generative models for solving physics-based inverse problems

A Dasgupta, J Murgoitio-Esandi, D Ray… - … 2023 Workshop on …, 2023 - openreview.net
We propose to sample from high-dimensional posterior distributions arising in physics-
based inverse problems using conditional score-based generative models. The proposed …