Image Deblurring

Follow this topic Ask about this topic

Image deblurring aims to recover sharp detail from images smeared by camera or scene motion, defocus, turbulence, and other optical effects. Methods range from blind and non-blind inverse-problem solvers and deep unrolling to CNNs, Transformers, state-space models, and diffusion or flow-based generative methods. Work also uses multiple frames, event-camera data, and 3D scene models, with benchmarks such as GoPro, HIDE, RealBlur, and DPDD testing motion and defocus restoration. A central challenge is transferring gains from synthetic data and standard metrics to real cameras and difficult scenes while balancing sharpness, fidelity, hallucination risk, and computational cost.

Latest papers

63 papers8 papers in the last four weeks, up 14% on the four weeks before. 0.0% of all new papers.

A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP
Aug 4, 2025Minh-Hai Nguyen, Edouard Pauwels, Pierre WeissImage Deblurring Bayesian Inference
IRIT, Toulouse University, Toulouse, France · Toulouse School of Economics, Universit´e Toulouse Capitole et IUF, Toulouse, France
SloMoDeblur: A Large-Scale Smartphone Image Deblurring Dataset
Jun 24, 2025Syed Mumtahin Mahmud, Mahdi Mohd Hossain Noki, Prothito Shovon Majumder +4Image Deblurring
Cognitive Agents and Interaction Lab, Department of Computer Science and Engineering, University of Dhaka, Dhaka-1000, Bangladesh
Efficient Concertormer for Image Deblurring and Beyond
Apr 9, 2024Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien +1Image Deblurring Transformer Attention

Aug 4, 2025J/K move · Enter open · S save

A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP

Minh-Hai Nguyen, Edouard Pauwels, Pierre Weiss

IRIT, Toulouse University, Toulouse, France · Toulouse School of Economics, Universit´e Toulouse Capitole et IUF, Toulouse, France

Image Deblurring Bayesian Inference MAP Estimation Image Inverse Problems

Open paper AskPDF arXiv

Maximum A Posteriori (MAP) estimation is a cornerstone framework for blind inverse problems, where an image and a forward operator are jointly estimated as the maximizers of a posterior distribution. In applications such as blind deblurring, this principle is used to recover sharp images from degraded observations. In this paper, we analyze the recovery guarantees of MAP-based methods by adopting a Morse--Bott framework. We model the image potential as a Morse--Bott function, where natural images are modeled as residing locally on a critical submanifold. This means that while the potential is locally flat along the

natural'' directions of the image manifold, it is strictly convex in the directions normal to it. We demonstrate that this Morse--Bott hypothesis aligns with the structural properties of state-of-the-art learned priors, a finding we validate through an experimental analysis of the potential landscape and its Hessian spectrum. Our theoretical results show that, in a neighborhood of the ground-truth image and operator, the posterior admits local minimizers that are stable both with respect to initialization (gradient descents converge to the same minimizer) and to small perturbations of the data (solutions vary smoothly with the observations). This local stability potentially provides a theoretical justification for the empirical success of well designed gradient-based optimization in these settings. However, we also demonstrate that this local stability is a **local** property: the

blurry trap'', well-known for sparse priors in blind deconvolution, persists even with state-of-the-art learned priors. Our findings demonstrate that the failure of MAP in blind deconvolution is not a limitation of prior quality, but an intrinsic characteristic of the landscape. We conclude that successful recovery depends on strategic initialization around favorable local minima.

Latest papers

A Morse-Bott Framework for Blind Inverse Problems: Local Recovery Guarantees and the Failure of the MAP

SloMoDeblur: A Large-Scale Smartphone Image Deblurring Dataset

Efficient Concertormer for Image Deblurring and Beyond