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...
Egile Nagusiak: | Ek, CH, Torr, PHS, Lawrence, ND |
---|---|
Formatua: | Conference item |
Hizkuntza: | English |
Argitaratua: |
Springer
2008
|
Antzeko izenburuak
-
Ambiguity modeling in latent spaces
nork: Ek, CH, et al.
Argitaratua: (2008) -
PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
nork: Vineet, V, et al.
Argitaratua: (2013) -
Surface Approximation by Means of Gaussian Process Latent Variable Models and Line Element Geometry
nork: Ivan De Boi, et al.
Argitaratua: (2023-01-01) -
Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
nork: Kohli, P, et al.
Argitaratua: (2008) -
Discriminative Gaussian Process Latent Variable Model for Classification
nork: Urtasun, Raquel, et al.
Argitaratua: (2007)