Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs

For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typicall...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer vision Vol. 133; no. 10; pp. 6953 - 6970
Main Authors: Ren, Dongwei, Shu, Xinya, Li, Yu, Wu, Xiaohe, Li, Jin, Zuo, Wangmeng
Format: Journal Article
Language:English
Published: New York Springer US 01.10.2025
Springer Nature B.V
Subjects:
Artificial Intelligence
Blurring
Cameras
Computer Imaging
Computer Science
Datasets
Deep learning
Design
Effectiveness
Image acquisition
Image Processing and Computer Vision
Learning
Misalignment
Modules
Neural networks
Pattern Recognition
Pattern Recognition and Graphics
Source code
Supervision
Vision
Isotropic blur kernels
Reblurring model
Image deblurring
Defocus deblurring
ISSN:0920-5691, 1573-1405
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For single image defocus deblurring, acquiring well-aligned training pairs (or training triplets), i.e. , a defocus blurry image, an all-in-focus sharp image (and a defocus blur map), is a challenging task for developing effective deblurring models. Existing image defocus deblurring methods typically rely on training data collected by specialized imaging equipment, with the assumption that these pairs or triplets are perfectly aligned. However, in practical scenarios involving the collection of real-world data, direct acquisition of training triplets is infeasible, and training pairs inevitably encounter spatial misalignment issues. In this work, we introduce a reblurring-guided learning framework for single image defocus deblurring, enabling the learning of a deblurring network even with misaligned training pairs. By reconstructing spatially variant isotropic blur kernels, our reblurring module ensures spatial consistency between the deblurred image, the reblurred image and the input blurry image, thereby addressing the misalignment issue while effectively extracting sharp textures from the all-in-focus sharp image. Moreover, spatially variant blur can be derived from the reblurring module, and serve as pseudo supervision for defocus blur map during training, interestingly transforming training pairs into training triplets. To leverage this pseudo supervision, we propose a lightweight defocus blur estimator coupled with a fusion block, which enhances deblurring performance through seamless integration with state-of-the-art deblurring networks. Additionally, we have collected a new dataset for single image defocus deblurring (SDD) with typical misalignments, which not only validates our proposed method but also serves as a benchmark for future research. The effectiveness of our method is validated by notable improvements in both quantitative metrics and visual quality across several datasets with real-world defocus blurry images, including DPDD, RealDOF, DED, and our SDD. The source code and dataset are available at  https://github.com/ssscrystal/Reblurring-guided-JDRL .
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-025-02522-3