Show simple item record

dc.contributor.authorSu, Shuochen
dc.contributor.authorDelbracio, Mauricio
dc.contributor.authorWang, Jue
dc.contributor.authorSapiro, Guillermo
dc.contributor.authorHeidrich, Wolfgang
dc.contributor.authorWang, Oliver
dc.date.accessioned2017-12-28T07:32:12Z
dc.date.available2017-12-28T07:32:12Z
dc.date.issued2016-11-25
dc.identifier.urihttp://hdl.handle.net/10754/626481
dc.description.abstractMotion 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 aligning 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 which requires high level scene understanding. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-to-end to learn how to accumulate information across frames. To train this network, we collected a dataset of real videos recorded with a high framerate 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.
dc.publisherarXiv
dc.relation.urlhttp://arxiv.org/abs/1611.08387v1
dc.relation.urlhttp://arxiv.org/pdf/1611.08387v1
dc.rightsArchived with thanks to arXiv
dc.titleDeep video deblurring
dc.typePreprint
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentComputer Science Program
dc.contributor.departmentVisual Computing Center (VCC)
dc.eprint.versionPre-print
dc.contributor.institutionThe Univerity of British Columbia
dc.contributor.institutionUniversidad de la Republica
dc.contributor.institutionAdobe Research
dc.contributor.institutionDuke University
dc.identifier.arxivid1611.08387
kaust.personHeidrich, Wolfgang
dc.versionv1
refterms.dateFOA2018-06-14T05:31:05Z


Files in this item

Thumbnail
Name:
1611.08387v1.pdf
Size:
8.178Mb
Format:
PDF
Description:
Preprint

This item appears in the following Collection(s)

Show simple item record