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...
Główni autorzy: | Ek, CH, Torr, PHS, Lawrence, ND |
---|---|
Format: | Conference item |
Język: | English |
Wydane: |
Springer
2008
|
Podobne zapisy
-
Ambiguity modeling in latent spaces
od: Ek, CH, i wsp.
Wydane: (2008) -
PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
od: Vineet, V, i wsp.
Wydane: (2013) -
Surface Approximation by Means of Gaussian Process Latent Variable Models and Line Element Geometry
od: Ivan De Boi, i wsp.
Wydane: (2023-01-01) -
Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
od: Kohli, P, i wsp.
Wydane: (2008) -
POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
od: Bray, M, i wsp.
Wydane: (2006)