Smooth Loops from Unconstrained Video

dc.contributor.authorSevilla-Lara, Lauraen_US
dc.contributor.authorWulff, Jonasen_US
dc.contributor.authorSunkavalli, Kalyanen_US
dc.contributor.authorShechtman, Elien_US
dc.contributor.editorJaakko Lehtinen and Derek Nowrouzezahraien_US
dc.date.accessioned2015-06-23T04:48:38Z
dc.date.available2015-06-23T04:48:38Z
dc.date.issued2015en_US
dc.description.abstractConverting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence-based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch-based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.en_US
dc.description.number4en_US
dc.description.sectionheadersExposure and Videoen_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume34en_US
dc.identifier.doi10.1111/cgf.12682en_US
dc.identifier.pages099-107en_US
dc.identifier.urihttps://doi.org/10.1111/cgf.12682en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleSmooth Loops from Unconstrained Videoen_US
Files