aiqbench analysis
This research introduces a massive new dataset derived from smartphone slow-motion video to rigorously benchmark image deblurring models under realistic motion conditions. By exposing state-of-the-art algorithms to complex scenarios involving varying object and camera motions, the study highlights significant performance gaps that current methods struggle to address in real-world settings. The work advances computer vision by providing a critical resource for developing more robust and generalizable deep learning architectures for image restoration tasks.
Deblurring in the Wild: A Real-World Image Deblurring Dataset from Smartphone High-Speed Videos
arXiv:2506.19445v4 Announce Type: cross 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.
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.
8 pages (without references), 3 figures. Dataset this https URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2506.19445 [cs.CV]
(or arXiv:2506.19445v4 [cs.CV] for this version)
Full text under the publisher's open licence · 148 words
Related coverage
WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relighting
arXiv · Sep 9, 2026
MODEST: Multi-Optics Depth-of-Field Stereo Dataset
arXiv · Aug 6, 2026
Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and Difference-Fusion Framework
arXiv · Sep 3, 2026
2026 BAIR Graduate Showcase
BAIR Blog · Jul 1, 2026