Separable spatiotemporal priors for convex reconstruction of time-varying 3D point clouds
Contribuinte(s) |
Fleet, D. Pajdla, T. Schiele, B. Tuytelaars, T. |
---|---|
Data(s) |
2014
|
Resumo |
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. |
Identificador | |
Publicador |
Springer International Publishing |
Relação |
DOI:10.1007/978-3-319-10578-9_14 Simon, Tomas, Valmadre, Jack, Matthews, Iain, & Sheikh, Yaser (2014) Separable spatiotemporal priors for convex reconstruction of time-varying 3D point clouds. In Fleet, D., Pajdla, T., Schiele, B., & Tuytelaars, T. (Eds.) Computer Vision – ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part III [Lecture Notes in Computer Science], Springer International Publishing, Zurich, Switzerland, pp. 204-219. |
Direitos |
Copyright 2014 Springer International Publishing Switzerland |
Fonte |
School of Electrical Engineering & Computer Science; Science & Engineering Faculty |
Palavras-Chave | #Matrix normal #trace-norm #spatiotemporal #missing data |
Tipo |
Conference Paper |