dc.contributor.author | Croci, Simone | en_US |
dc.contributor.author | Smolic, Aljoscha | en_US |
dc.contributor.author | Wang, Oliver | en_US |
dc.contributor.editor | Michael Bronstein and Jean Favre and Kai Hormann | en_US |
dc.date.accessioned | 2014-02-01T16:26:19Z | |
dc.date.available | 2014-02-01T16:26:19Z | |
dc.date.issued | 2013 | en_US |
dc.identifier.isbn | 978-3-905674-51-4 | en_US |
dc.identifier.uri | http://dx.doi.org/10.2312/PE.VMV.VMV13.229-230 | en_US |
dc.description.abstract | In this work, we present a method for computing 3D contours from the silhouettes of objects in multiple views. Our approach unwraps contours into 1D signals and computes an efficient, globally optimal alignment using a modified dynamic time warping technique. Using our method, we can approximate real model geometry by interpolating the 3D contour on the billboard plane, thereby reducing the stereo problem to 1D and allowing for much more efficient and robust computation methods. | en_US |
dc.publisher | The Eurographics Association | en_US |
dc.subject | I.4.9 [Image Processing and Computer Vision] | en_US |
dc.subject | Applications | en_US |
dc.title | Dynamic Time Warping Based 3D Contours | en_US |
dc.description.seriesinformation | Vision, Modeling & Visualization | en_US |