# Stop Denoising Your Blurs

arXiv: https://arxiv.org/abs/2605.25014 · HTML: https://mlsanity.com/paper/2605.25014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 24 May 2026.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise](https://mlsanity.com/paper/2208.09392/) (2022)
- [DiffIR: Efficient Diffusion Model for Image Restoration](https://mlsanity.com/paper/2303.09472/) (2023)
- [Generative Modelling With Inverse Heat Dissipation](https://mlsanity.com/paper/2206.13397/) (2022)
- [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022)
- [Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration](https://mlsanity.com/paper/2303.11435/) (2023)
- [Hierarchical Integration Diffusion Model for Realistic Image Deblurring](https://mlsanity.com/paper/2305.12966/) (2023)
- [Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis](https://mlsanity.com/paper/2207.11192/) (2022)
- [BlurDM: A Blur Diffusion Model for Image Deblurring](https://mlsanity.com/paper/2512.03979/) (2025)
- [FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring](https://mlsanity.com/paper/2510.01641/) (2025)

## Abstract (arXiv)

In recent times, diffusion models have achieved remarkable performance in image restoration tasks. Their core mechanism relies on the restricted presumption of degradation prior to the additive noise operation. However, the blur model, one of the most widely studied degradation formulations, violates this assumption, as it is inherently based on convolution rather than addition. In this paper, we introduce ConvDiff, a novel diffusion based framework that substitutes the additive operation with convolution for the task of image deblurring. In the forward process, we construct a meaningful trajectory from the clean image to its blurred counterpart by exploiting the frequency domain characteristics of convolution, rather than progressively corrupting the image with additive noise. While the current work instantiates this framework for Gaussian blur, where frequency-domain decomposition yields closed-form and physically valid intermediate states, the underlying principle of constructing degradation trajectories from the blur operator extends naturally to other blur families. This formulation bridges the gap between the mathematical principles of blurring and the iterative design of diffusion-based restoration algorithms, enabling more physically grounded and effective image restoration models.