Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos

TL;DR

This paper introduces a large-scale real-world image deblurring dataset from smartphone videos, providing a challenging benchmark that reveals the limitations of current deblurring models and aims to advance robust solutions.

Contribution

The creation of the largest real-world deblurring dataset from smartphone videos, with over 42,000 high-resolution image pairs, enabling more realistic and diverse model evaluation.

Findings

State-of-the-art models perform poorly on the new dataset.

The dataset includes diverse indoor and outdoor scenes.

Benchmark results highlight the need for more robust deblurring methods.

Abstract

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.