Consensus Skeleton for Non-rigid Space-time Registration

dc.contributor.authorZheng, Q.en_US
dc.contributor.authorSharf, A.en_US
dc.contributor.authorTagliasacchi, A.en_US
dc.contributor.authorChen, B.en_US
dc.contributor.authorZhang, H.en_US
dc.contributor.authorSheffer, A.en_US
dc.contributor.authorCohen-Or, D.en_US
dc.date.accessioned2015-02-23T16:41:57Z
dc.date.available2015-02-23T16:41:57Z
dc.date.issued2010en_US
dc.description.abstractWe introduce the notion of consensus skeletons for non-rigid space-time registration of a deforming shape. Instead of basing the registration on point features, which are local and sensitive to noise, we adopt the curve skeleton of the shape as a global and descriptive feature for the task. Our method uses no template and only assumes that the skeletal structure of the captured shape remains largely consistent over time. Such an assumption is generally weaker than those relying on large overlap of point features between successive frames, allowing for more sparse acquisition across time. Building our registration framework on top of the low-dimensional skeleton-time structure avoids heavy processing of dense point or volumetric data, while skeleton consensusization provides robust handling of incompatibilities between per-frame skeletons. To register point clouds from all frames, we deform them by their skeletons, mirroring the skeleton registration process, to jump-start a non-rigid ICP. We present results for non-rigid space-time registration under sparse and noisy spatio-temporal sampling, including cases where data was captured from only a single view.en_US
dc.description.number2en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume29en_US
dc.identifier.doi10.1111/j.1467-8659.2009.01633.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages635-644en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2009.01633.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing Ltden_US
dc.titleConsensus Skeleton for Non-rigid Space-time Registrationen_US
Files