Saved in:
Bibliographic Details
Main Authors: Carbajal, Guillermo, Vitoria, Patricia, Lezama, José, Musé, Pablo
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2209.12675
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915222323724288
author Carbajal, Guillermo
Vitoria, Patricia
Lezama, José
Musé, Pablo
author_facet Carbajal, Guillermo
Vitoria, Patricia
Lezama, José
Musé, Pablo
contents Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains a challenging task. In this paper, we first review the limitations of existing deblurring benchmark datasets and analyze the underlying causes for deblurring networks' lack of generalization to blurry images in the wild. Based on this analysis, we propose an efficient procedural methodology to generate sharp/blurred image pairs based on a simple yet effective model. This allows for generating virtually unlimited diverse training pairs mimicking realistic blur properties. We demonstrate the effectiveness of the proposed dataset by training existing deblurring architectures on the simulated pairs and performing cross-dataset evaluation on three standard datasets of real blurred images. When training with the proposed method, we observed superior generalization performance for the ultimate task of deblurring real motion-blurred photos of dynamic scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2209_12675
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images
Carbajal, Guillermo
Vitoria, Patricia
Lezama, José
Musé, Pablo
Computer Vision and Pattern Recognition
Successfully training end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining such datasets remains a challenging task. In this paper, we first review the limitations of existing deblurring benchmark datasets and analyze the underlying causes for deblurring networks' lack of generalization to blurry images in the wild. Based on this analysis, we propose an efficient procedural methodology to generate sharp/blurred image pairs based on a simple yet effective model. This allows for generating virtually unlimited diverse training pairs mimicking realistic blur properties. We demonstrate the effectiveness of the proposed dataset by training existing deblurring architectures on the simulated pairs and performing cross-dataset evaluation on three standard datasets of real blurred images. When training with the proposed method, we observed superior generalization performance for the ultimate task of deblurring real motion-blurred photos of dynamic scenes.
title Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2209.12675