# Diffusion models for inverse problems

Source: [Diffusion models for inverse problems](<https://www.sota2.com/research/paper/68fa7a691e209131cea83090>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:20:02.433Z

Authors: Hyungjin Chung, Jeongsol Kim, Jong Chul Ye

Published: 2025-08-04T01:26:06.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Multi-Image Super-Resolution on 100 subjects MRI dataset Axial & Coronal](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-100-subjects-mri-dataset-axial-and-coronal.md>): Multi-image Super-resolution; 100 subjects MRI dataset Axial & Coronal; PSNR: 30.23.

- [Multi-Image Super-Resolution on 100 subjects MRI dataset Axial, Coronal & Sagittal](<https://www.sota2.com/research/sota/multi-image-super-resolution-on-100-subjects-mri-dataset-axial-coronal-and-sagittal.md>): Multi-image Super-resolution; 100 subjects MRI dataset Axial, Coronal & Sagittal; PSNR: 32.14.

- [Single-Image Super-Resolution on 100 subjects MRI dataset Axial](<https://www.sota2.com/research/sota/single-image-super-resolution-on-100-subjects-mri-dataset-axial.md>): Single Image Super-Resolution; 100 subjects MRI dataset Axial; PSNR: 27.92.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.01975>)

[PDF](<https://arxiv.org/pdf/2508.01975.pdf>)
