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...
Главные авторы: | Ek, CH, Torr, PHS, Lawrence, ND |
---|---|
Формат: | Conference item |
Язык: | English |
Опубликовано: |
Springer
2008
|
Схожие документы
-
Ambiguity modeling in latent spaces
по: Ek, CH, и др.
Опубликовано: (2008) -
PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
по: Vineet, V, и др.
Опубликовано: (2013) -
Surface Approximation by Means of Gaussian Process Latent Variable Models and Line Element Geometry
по: Ivan De Boi, и др.
Опубликовано: (2023-01-01) -
Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
по: Kohli, P, и др.
Опубликовано: (2008) -
Discriminative Gaussian Process Latent Variable Model for Classification
по: Urtasun, Raquel, и др.
Опубликовано: (2007)