SimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithm

Simple item page
dc.contributor.authorTao, Michaelen_US
dc.contributor.authorBai, Jiaminen_US
dc.contributor.authorKohli, Pushmeeten_US
dc.contributor.authorParis, Sylvainen_US
dc.contributor.editorP. Cignoni and T. Ertlen_US
dc.date.accessioned2015-02-28T06:52:25Z
dc.date.available2015-02-28T06:52:25Z
dc.date.issued2012en_US
dc.description.abstractOptical flow is a critical component of video editing applications, e.g. for tasks such as object tracking, segmentation, and selection. In this paper, we propose an optical flow algorithm called SimpleFlow whose running times increase sublinearly in the number of pixels. Central to our approach is a probabilistic representation of the motion flow that is computed using only local evidence and without resorting to global optimization. To estimate the flow in image regions where the motion is smooth, we use a sparse set of samples only, thereby avoiding the expensive computation inherent in traditional dense algorithms. We show that our results can be used as is for a variety of video editing tasks. For applications where accuracy is paramount, we use our result to bootstrap a global optimization. This significantly reduces the running times of such methods without sacrificing accuracy. We also demonstrate that the SimpleFlow algorithm can process HD and 4K footage in reasonable times.en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume31
dc.identifier.doi10.1111/j.1467-8659.2012.03013.x
dc.identifier.issn1467-8659en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2012.03013.xen_US
dc.publisherThe Eurographics Association and John Wiley and Sons Ltd.en_US
dc.titleSimpleFlow: A Non-iterative, Sublinear Optical Flow Algorithmen_US
Files
Collections
31-Issue 2
Full Papers 2012 - CGF 31-Issue 2