# Kernel Diffusion: An Alternate Approach to Blind Deconvolution

arXiv: https://arxiv.org/abs/2312.02319 · HTML: https://mlsanity.com/paper/2312.02319/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2023.

## Built on by (most cited first, 13 of 13)

- [DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models](https://mlsanity.com/paper/2405.16749/) (2024)
- [Tutorial on Diffusion Models for Imaging and Vision](https://mlsanity.com/paper/2403.18103/) (2024)
- [Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models](https://mlsanity.com/paper/2408.07472/) (2024)
- [Learning Phase Distortion with Selective State Space Models for Video Turbulence Mitigation](https://mlsanity.com/paper/2504.02697/) (2025)
- [Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models](https://mlsanity.com/paper/2505.20789/) (2025)
- [Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching](https://mlsanity.com/paper/2506.14605/) (2025)
- [FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurring](https://mlsanity.com/paper/2510.01641/) (2025)
- [ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstruction](https://mlsanity.com/paper/2411.16535/) (2024)
- [Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion](https://mlsanity.com/paper/2412.00557/) (2024)
- [On the Sample Complexity of Learning for Blind Inverse Problems](https://mlsanity.com/paper/2512.23405/) (2025)
- [Outlier-Robust Diffusion Solvers for Inverse Problems](https://mlsanity.com/paper/2605.09477/) (2026)
- [MoTDiff: High-resolution Motion Trajectory estimation from a single blurred image using Diffusion models](https://mlsanity.com/paper/2510.26173/) (2025)
- [Diffusion Algorithm for Metalens Optical Aberration Correction](https://mlsanity.com/paper/2511.12689/) (2025)

## Abstract (arXiv)

Blind deconvolution problems are severely ill-posed because neither the underlying signal nor the forward operator are not known exactly. Conventionally, these problems are solved by alternating between estimation of the image and kernel while keeping the other fixed. In this paper, we show that this framework is flawed because of its tendency to get trapped in local minima and, instead, suggest the use of a kernel estimation strategy with a non-blind solver. This framework is employed by a diffusion method which is trained to sample the blur kernel from the conditional distribution with guidance from a pre-trained non-blind solver. The proposed diffusion method leads to state-of-the-art results on both synthetic and real blur datasets.