Qiu, J. and Wang, X. and Maybank, Stephen J. and Tao, D. (2020) World from blur. IEEE Computer Society Conference on Computer Vision and Pattern Recognition , ISSN 1063-6919.
![[img]](https://eprints.bbk.ac.uk/style/images/fileicons/text.png) |
Text
World-from-Blur.pdf - Author's Accepted Manuscript Restricted to Repository staff only Download (2MB) | Request a copy |
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.
Metadata
| Item Type: | Article |
|---|---|
| Additional Information: | (c) 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. |
| School: | Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences |
| Depositing User: | Stephen Maybank |
| Date Deposited: | 12 Mar 2019 14:15 |
| Last Modified: | 09 Aug 2023 12:46 |
| URI: | https://eprints.bbk.ac.uk/id/eprint/26643 |
Statistics
Additional statistics are available via IRStats2.
Archive Staff Only (login required)
