Gaussian process latent variable models for human pose estimation
We describe a method for recovering 3D human body pose from silhouettes. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM) [1] encapsulating both pose and silhouette features Our method is generative, this allows us to model the ambiguities of a...
主要な著者: | Ek, CH, Torr, PHS, Lawrence, ND |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Springer
2008
|
類似資料
-
Ambiguity modeling in latent spaces
著者:: Ek, CH, 等
出版事項: (2008) -
PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
著者:: Vineet, V, 等
出版事項: (2013) -
Surface Approximation by Means of Gaussian Process Latent Variable Models and Line Element Geometry
著者:: Ivan De Boi, 等
出版事項: (2023-01-01) -
Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
著者:: Kohli, P, 等
出版事項: (2008) -
Discriminative Gaussian Process Latent Variable Model for Classification
著者:: Urtasun, Raquel, 等
出版事項: (2007)