Paper Info
Title
Separable Spatiotemporal Priors For Convex Reconstruction Of Time-Varying 3d Point Clouds
Abstract
Reconstructing 3D motion data is highly under-constrained due to several common sources of data loss during measurement, such as projection, occlusion, or miscorrespondence. We present a statistical model of 3D motion data, based on the Kronecker structure of the spatiotemporal covariance of natural motion, as a prior on 3D motion. This prior is expressed as a matrix normal distribution, composed of separable and compact row and column covariances. We relate the marginals of the distribution to the shape, trajectory, and shape-trajectory models of prior art. When the marginal shape distribution is not available from training data, we show how placing a hierarchical prior over shapes results in a convex MAP solution in terms of the trace-norm. The matrix normal distribution, fit to a single sequence, outperforms state-of-the-art methods at reconstructing 3D motion data in the presence of significant data loss, while providing covariance estimates of the imputed points.
Year
DOI
Venue
2014
10.1007/978-3-319-10578-9_14
COMPUTER VISION - ECCV 2014, PT III
Keywords
Field
DocType
Matrix normal, trace-norm, spatiotemporal, missing data
Matrix normal distribution,Kronecker delta,Pattern recognition,Statistical model,Artificial intelligence,Missing data,Point cloud,Prior probability,Trajectory,Mathematics,Covariance
Conference
Volume
ISSN
Citations 
8691
0302-9743
10
PageRank 
References 
Authors
0.46
36
4
Name
Order
Citations
PageRank
Tomas Simon122213.27
Jack Valmadre246614.08
Iain Matthews34900253.61
Yaser Sheikh4211892.13