paper-with-me

홈 › Papers

Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation

2024-04-29 · Pascal Fernsel, Željko Kereta, Alexander Denker

The incorporation of generative models as regularisers within variational formulations for inverse problems has proven effective across numerous image reconstruction tasks. However, the resulting optimisation problem is often non-convex and challenging to solve. In this work, we show that score-based generative models (SGMs) can be used in a graduated optimisation framework to solve inverse problems. We show that the resulting graduated non-convexity flow converge to stationary points of the original problem and provide a numerical convergence analysis of a 2D toy example. We further provide experiments on computed tomography image reconstruction, where we show that this framework is able to recover high-quality images, independent of the initial value. The experiments highlight the potential of using SGMs in graduated optimisation frameworks. The source code is publicly available on GitHub.

📄 PDF Abstract BibTeX arXiv:2404.18699

Code (1)

alexdenker/gradopt-sgm 공식 구현 pytorch

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

Taming Score-Based Diffusion Priors for Infinite-Dimensional Nonlinear Inverse Problems

2024-05-24 · Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna 외

This work introduces a sampling method capable of solving Bayesian inverse problems in function space. It does not assume the log-concavity of the likelihood, meaning that it is compatible with nonlinear inverse problems…

Denoising

Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems

2025-05-23 · Lorenzo Baldassari, Josselin Garnier, Knut Solna, Maarten V. de Hoop

Designing algorithms for solving high-dimensional Bayesian inverse problems directly in infinite-dimensional function spaces - where such problems are naturally formulated - is crucial to ensure stability and convergence…

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

2023-06-06 · NeurIPS 2023 11

Plug-and-Play (PnP) methods are efficient iterative algorithms for solving ill-posed image inverse problems. PnP methods are obtained by using deep Gaussian denoisers instead of the proximal operator or the gradient-desc…

Image Restoration

Convergence of the Forward-Backward Algorithm: Beyond the Worst Case with the Help of Geometry

2017-03-28 · Guillaume Garrigos, Lorenzo Rosasco, Silvia Villa

We provide a comprehensive study of the convergence of the forward-backward algorithm under suitable geometric conditions, such as conditioning or {\L}ojasiewicz properties. These geometrical notions are usually local by…

Solving Diffusion Inverse Problems with Restart Posterior Sampling

2025-11-24 · Bilal Ahmed, Joseph G. Makin arxiv

Inverse problems are fundamental to science and engineering, where the goal is to infer an underlying signal or state from incomplete or noisy measurements. Recent approaches employ diffusion models as powerful implicit …