Skip to main content

Deep video deblurring for hand-held cameras

Publication ,  Conference
Su, S; Delbracio, M; Wang, J; Sapiro, G; Heidrich, W; Wang, O
Published in: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
November 6, 2017

Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods that aggregate information must therefore be able to identify which regions have been accurately aligned and which have not, a task that requires high level scene understanding. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-toend to learn how to accumulate information across frames. To train this network, we collected a dataset of real videos recorded with a high frame rate camera, which we use to generate synthetic motion blur for supervision. We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.

Duke Scholars

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

ISBN

9781538604571

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

237 / 246
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., & Wang, O. (2017). Deep video deblurring for hand-held cameras. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (Vol. 2017-January, pp. 237–246). https://doi.org/10.1109/CVPR.2017.33
Su, S., M. Delbracio, J. Wang, G. Sapiro, W. Heidrich, and O. Wang. “Deep video deblurring for hand-held cameras.” In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017-January:237–46, 2017. https://doi.org/10.1109/CVPR.2017.33.
Su S, Delbracio M, Wang J, Sapiro G, Heidrich W, Wang O. Deep video deblurring for hand-held cameras. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017. p. 237–46.
Su, S., et al. “Deep video deblurring for hand-held cameras.” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, 2017, pp. 237–46. Scopus, doi:10.1109/CVPR.2017.33.
Su S, Delbracio M, Wang J, Sapiro G, Heidrich W, Wang O. Deep video deblurring for hand-held cameras. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. 2017. p. 237–246.

Published In

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

DOI

ISBN

9781538604571

Publication Date

November 6, 2017

Volume

2017-January

Start / End Page

237 / 246