We introduce the largest real-world image deblurring dataset constructed from smartphone slow-motion videos. Using 240 frames captured over one second, we simulate realistic long-exposure blur by averaging frames to produce blurry images, while using the temporally centered frame as the sharp reference. Our dataset contains over 42,000 high-resolution blur-sharp image pairs, making it approximately 10 times larger than widely used datasets, with 8 times the amount of different scenes, including indoor and outdoor environments, with varying object and camera motions. We benchmark multiple state-of-the-art (SOTA) deblurring models on our dataset and observe significant performance degradation, highlighting the complexity and diversity of our benchmark. Our dataset serves as a challenging new benchmark to facilitate robust and generalizable deblurring models.
@article{arxiv.2506.19445,
title = {Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos},
author = {Syed Mumtahin Mahmud and Mahdi Mohd Hossain Noki and Prothito Shovon Majumder and Abdul Mohaimen Al Radi and Sudipto Das Sukanto and Afia Lubaina and Md. Mosaddek Khan},
journal= {arXiv preprint arXiv:2506.19445},
year = {2025}
}