Diffusion models for inverse problems
Preprint
Abstract
Using diffusion priors to solve inverse problems in imaging have significantly matured over the years. In this chapter, we review the various different approaches that were proposed over the years. We categorize the approaches into the more classic explicit approximation approaches and others, which include variational inference, sequential monte carlo, and decoupled data consistency. We cover the extension to more challenging situations, including blind cases, high-dimensional data, and problems under data scarcity and distribution mismatch. More recent approaches that aim to leverage multimodal information through texts are covered. Through this chapter, we aim to (i) distill the common mathematical threads that connect these algorithms, (ii) systematically contrast their assumptions and performance trade-offs across representative inverse problems, and (iii) spotlight the open theoretical and practical challenges by clarifying the landscape of diffusion model based inverse problem solvers.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Test-Time Adaptation Improves Inverse Problem Solving With Patch-Based Diffusion ModelsIEEE Transactions on Computational Imaging, 2025
- Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image ReconstructionIEEE Transactions on Medical Imaging, 2025
- Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems2024
- Score-Based Diffusion Models as Principled Priors for Inverse Imaging2023
- Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models2023
- ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction AlgorithmsIEEE Transactions on Medical Imaging, 2022
- CryoGAN: A New Reconstruction Paradigm for Single-Particle Cryo-EM Via Deep Adversarial LearningIEEE Transactions on Computational Imaging, 2021
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image DenoisingIEEE Transactions on Image Processing, 2017
- Generalized SURE for Exponential Families: Applications to RegularizationIEEE Transactions on Signal Processing, 2008
- Reverse-time diffusion equation modelsStochastic Processes and their Applications, 1982