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 Simon | 1 | 222 | 13.27 |
Jack Valmadre | 2 | 466 | 14.08 |
Iain Matthews | 3 | 4900 | 253.61 |
Yaser Sheikh | 4 | 2118 | 92.13 |