# Unpaired Deblurring via Decoupled Diffusion Model

arXiv: https://arxiv.org/abs/2502.01522 · HTML: https://mlsanity.com/paper/2502.01522/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 0 of its 2 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Built on by (most cited first, 3 of 3)

- [FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring](https://mlsanity.com/paper/2510.01641/) (2025)
- [Generative Manifold Distillation: Aligning Restoration Trajectories with Natural Image Prior](https://mlsanity.com/paper/2512.11121/) (2025)
- [PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video](https://mlsanity.com/paper/2610.01279/) (2026)

## Abstract (arXiv)

Generative diffusion models trained on large-scale datasets have achieved remarkable progress in image synthesis. In favor of their ability to supplement missing details and generate aesthetically pleasing contents, recent works have applied them to image deblurring via training an adapter on blurry-sharp image pairs to provide structural conditions for restoration. However, acquiring substantial amounts of realistic paired data is challenging and costly in real-world scenarios. On the other hand, relying solely on synthetic data often results in overfitting, leading to unsatisfactory performance when confronted with unseen blur patterns. To tackle this issue, we propose UID-Diff, a generative-diffusion-based model designed to enhance deblurring performance on unknown domains by decoupling structural features and blur patterns through joint training on three specially designed tasks. We employ two Q-Formers as structural features and blur patterns extractors separately. The features extracted by them will be used for the supervised deblurring task on synthetic data and the unsupervised blur-transfer task by leveraging unpaired blurred images from the target domain simultaneously. We further introduce a reconstruction task to make the structural features and blur patterns complementary. This blur-decoupled learning process enhances the generalization capabilities of UID-Diff when encountering unknown blur patterns. Experiments on real-world datasets demonstrate that UID-Diff outperforms existing state-of-the-art methods in blur removal and structural preservation in various challenging scenarios.