/GradOpt-SGM

Primary LanguageJupyter NotebookMIT LicenseMIT

Reference Paper

This repository contains the codebase for the numerical experiments in the paper:

P. Fernsel, Z. Kereta, A. Denker Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation

Citations

If you find this work helpful please cite:

@article{fernsel2024convergence,
  title={Convergence Properties of Score-Based Models using Graduated Optimisation for Linear Inverse Problems},
  author={Fernsel, Pascal and Kereta, {\v{Z}}eljko and Denker, Alexander},
  journal={arXiv preprint arXiv:2404.18699},
  year={2024}
}

2D Toy Example

The folder 2D_toy_example contains the necessary codebase to reproduce the numerical experiments in the paper regarding the 2D inverse problem discussed in Section 4.1. Furthermore, the folder includes a README file with a detailed description of the considered 2D problem and a documentation of the codebase.

Computed Tomography