Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
This provides a challenging new benchmark for developing robust deblurring models, addressing the need for more realistic and diverse data in computer vision, though it is incremental as it builds on existing dataset creation methods.
The authors tackled the problem of real-world image deblurring by creating a large dataset from smartphone slow-motion videos, resulting in over 42,000 high-resolution blur-sharp image pairs that are 10 times larger and 8 times more diverse than existing datasets, and they found that state-of-the-art models perform significantly worse on it.
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.