Video Motion Stylization by 2D Rigidification

dc.contributor.authorDelanoy, Johannaen_US
dc.contributor.authorBousseau, Adrienen_US
dc.contributor.authorHertzmann, Aaronen_US
dc.contributor.editorKaplan, Craig S. and Forbes, Angus and DiVerdi, Stephenen_US
dc.date.accessioned2019-05-20T09:49:43Z
dc.date.available2019-05-20T09:49:43Z
dc.date.issued2019
dc.description.abstractThis paper introduces a video stylization method that increases the apparent rigidity of motion. Existing stylization methods often retain the 3D motion of the original video, making the result look like a 3D scene covered in paint rather than a 2D painting of a scene. In contrast, traditional hand-drawn animations often exhibit simplified in-plane motion, such as in the case of cut-out animations where the animator moves pieces of paper from frame to frame. Inspired by this technique, we propose to modify a video such that its content undergoes 2D rigid transforms. To achieve this goal, our approach applies motion segmentation and optimization to best approximate the input optical flow with piecewise-rigid transforms, and re-renders the video such that its content follows the simplified motion. The output of our method is a new video and its optical flow, which can be fed to any existing video stylization algorithm.en_US
dc.description.sectionheadersArt in Motion
dc.description.seriesinformationACM/EG Expressive Symposium
dc.identifier.doi10.2312/exp.20191072
dc.identifier.isbn978-3-03868-078-9
dc.identifier.pages11-19
dc.identifier.urihttps://doi.org/10.2312/exp.20191072
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/exp20191072
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectNon
dc.subjectphotorealistic rendering
dc.subjectMotion processing
dc.titleVideo Motion Stylization by 2D Rigidificationen_US
Files
Original bundle
Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
011-019.pdf
Size:
17.71 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
video_eg.mp4
Size:
146.17 MB
Format:
Unknown data format
Collections