# Single Image Blind Deblurring Using Multi-Scale Latent Structure Prior

arXiv: https://arxiv.org/abs/1906.04442 · HTML: https://mlsanity.com/paper/1906.04442/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [MC-Blur: A Comprehensive Benchmark for Image Deblurring](https://mlsanity.com/paper/2112.00234/) (2021)
- [FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring](https://mlsanity.com/paper/2204.07820/) (2022)
- [Multi-scale frequency separation network for image deblurring](https://mlsanity.com/paper/2206.00798/) (2022)
- [Blind Image Deconvolution Using Variational Deep Image Prior](https://mlsanity.com/paper/2202.00179/) (2022)
- [Deep learning in motion deblurring: current status, benchmarks and future prospects](https://mlsanity.com/paper/2401.05055/) (2024)
- [Deep Idempotent Network for Efficient Single Image Blind Deblurring](https://mlsanity.com/paper/2210.07122/) (2022)
- [Learning Parallax for Stereo Event-based Motion Deblurring](https://mlsanity.com/paper/2309.09513/) (2023)
- [Blind Non-Uniform Motion Deblurring using Atrous Spatial Pyramid Deformable Convolution and Deblurring-Reblurring Consistency](https://mlsanity.com/paper/2106.14336/) (2021)
- [Blind Image Deblurring with FFT-ReLU Sparsity Prior](https://mlsanity.com/paper/2406.08344/) (2024)
- [Deblur-Avatar: Animatable Avatars from Motion-Blurred Monocular Videos](https://mlsanity.com/paper/2501.13335/) (2025)
- [A Constrained Deformable Convolutional Network for Efficient Single Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur Kernels Estimation](https://mlsanity.com/paper/2208.10711/) (2022)
- [IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model](https://mlsanity.com/paper/2605.14337/) (2026)

## Abstract (arXiv)

Blind image deblurring is a challenging problem in computer vision, which aims to restore both the blur kernel and the latent sharp image from only a blurry observation. Inspired by the prevalent self-example prior in image super-resolution, in this paper, we observe that a coarse enough image down-sampled from a blurry observation is approximately a low-resolution version of the latent sharp image. We prove this phenomenon theoretically and define the coarse enough image as a latent structure prior of the unknown sharp image. Starting from this prior, we propose to restore sharp images from the coarsest scale to the finest scale on a blurry image pyramid, and progressively update the prior image using the newly restored sharp image. These coarse-to-fine priors are referred to as textitMulti-Scale Latent Structures (MSLS). Leveraging the MSLS prior, our algorithm comprises two phases: 1) we first preliminarily restore sharp images in the coarse scales; 2) we then apply a refinement process in the finest scale to obtain the final deblurred image. In each scale, to achieve lower computational complexity, we alternately perform a sharp image reconstruction with fast local self-example matching, an accelerated kernel estimation with error compensation, and a fast non-blind image deblurring, instead of computing any computationally expensive non-convex priors. We further extend the proposed algorithm to solve more challenging non-uniform blind image deblurring problem. Extensive experiments demonstrate that our algorithm achieves competitive results against the state-of-the-art methods with much faster running speed.