2025/08/08 by Daniel Feijoo, Paula Garrido-Mellado, Feijoo, Daniel +7
Computer Science · #Advanced Image Processing Techniques #Code (set theory) #Computational photography #Computer Vision and Pattern Recognition (cs.CV) #Deblurring #Decoding methods #Digital Media Forensic Detection #FOS: Computer and information sciences #Focus (optics) #Generalization #Image (mathematics) #Image and Signal Denoising Methods #Image restoration
paper · pdf · doi:10.48550/arxiv.2508.06228
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/08/08 · openalex created_date 2025/10/15 · openalex updated_date 2026/08/05
Image deblurring, removing blurring artifacts from images, is a fundamental task in computational photography and low-level computer vision. Existing approaches focus on specialized solutions tailored to particular blur types, thus, these solutions lack generalization. This limitation in current methods implies requiring multiple models to cover several blur types, which is not practical in many real scenarios. In this paper, we introduce the first all-in-one deblurring method capable of efficiently restoring images affected by diverse blur degradations, including global motion, local motion, blur in low-light conditions, and defocus blur. We propose a mixture-of-experts (MoE) decoding module, which dynamically routes image features based on the recognized blur degradation, enabling precise and efficient restoration in an end-to-end manner. Our unified approach not only achieves performance comparable to dedicated task-specific models, but also shows promising generalization to unseen blur scenarios, particularly when leveraging appropriate expert selection. Code available at https://github.com/cidautai/DeMoE.