BluRef: Unsupervised Image Deblurring with Dense-Matching References

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pham, Bang-Dang, Tran, Anh, Pham, Cuong, Hoai, Minh
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917342482530304
author Pham, Bang-Dang
Tran, Anh
Pham, Cuong
Hoai, Minh
author_facet Pham, Bang-Dang
Tran, Anh
Pham, Cuong
Hoai, Minh
contents This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14176
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BluRef: Unsupervised Image Deblurring with Dense-Matching References
Pham, Bang-Dang
Tran, Anh
Pham, Cuong
Hoai, Minh
Computer Vision and Pattern Recognition
This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.
title BluRef: Unsupervised Image Deblurring with Dense-Matching References
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.14176