Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908584764243968 |
|---|---|
| author | Mahmud, Syed Mumtahin Noki, Mahdi Mohd Hossain Majumder, Prothito Shovon Radi, Abdul Mohaimen Al Sukanto, Sudipto Das Lubaina, Afia Khan, Md. Mosaddek |
| author_facet | Mahmud, Syed Mumtahin Noki, Mahdi Mohd Hossain Majumder, Prothito Shovon Radi, Abdul Mohaimen Al Sukanto, Sudipto Das Lubaina, Afia Khan, Md. Mosaddek |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19445 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos Mahmud, Syed Mumtahin Noki, Mahdi Mohd Hossain Majumder, Prothito Shovon Radi, Abdul Mohaimen Al Sukanto, Sudipto Das Lubaina, Afia Khan, Md. Mosaddek Computer Vision and Pattern Recognition 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. |
| title | Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.19445 |