Cited 0 time in
Cited 7 time in
Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms
- Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms
- Rim, Jaesung; Lee, Haeyun; Won, Jucheol; Cho, Sunghyun
- Issue Date
- 16th European Conference on Computer Vision, ECCV 2020, 184-201
- Numerous learning-based approaches to single image deblurring for camera and object motion blurs have recently been proposed. To generalize such approaches to real-world blurs, large datasets of real blurred images and their ground truth sharp images are essential. However, there are still no such datasets, thus all the existing approaches resort to synthetic ones, which leads to the failure of deblurring real-world images. In this work, we present a large-scale dataset of real-world blurred images and ground truth sharp images for learning and benchmarking single image deblurring methods. To collect our dataset, we build an image acquisition system to simultaneously capture geometrically aligned pairs of blurred and sharp images, and develop a postprocessing method to produce high-quality ground truth images. We analyze the effect of our postprocessing method and the performance of existing deblurring methods. Our analysis shows that our dataset significantly improves deblurring quality for real-world blurred images. © 2020, Springer Nature Switzerland AG.
- Springer Science and Business Media Deutschland GmbH
There are no files associated with this item.
- ETC2. Conference Papers
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.