World from Blur
Abstract
What can we tell from a single motion-blurred image? We show in this paper that a 3D scene can be revealed. Unlike prior methods that focus on producing a deblurred image, we propose to estimate and take advantage of the hidden message of a blurred image, the relative motion trajectory, to restore the 3D scene collapsed during the exposure process. To this end, we train a deep network that jointly predicts the motion trajectory, the deblurred image, and the depth one, all of which in turn form a collaborative and self-supervised cycle that supervise one another to reproduce the input blurred image, enabling plausible 3D scene reconstruction from a single blurred image. We test the proposed model on several large-scale datasets we constructed based on benchmarks, as well as real-world blurred images, and show that it yields very encouraging quantitative and qualitative results.
Cite
Text
Qiu et al. "World from Blur." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019. doi:10.1109/CVPR.2019.00869Markdown
[Qiu et al. "World from Blur." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019.](https://mlanthology.org/cvpr/2019/qiu2019cvpr-world/) doi:10.1109/CVPR.2019.00869BibTeX
@inproceedings{qiu2019cvpr-world,
title = {{World from Blur}},
author = {Qiu, Jiayan and Wang, Xinchao and Maybank, Stephen J. and Tao, Dacheng},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2019},
doi = {10.1109/CVPR.2019.00869},
url = {https://mlanthology.org/cvpr/2019/qiu2019cvpr-world/}
}