Download now Free registration required
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. The true range of motion can therefore be represented by latent variables that span a low-dimensional space. This has often been used to make motion tracking easier. However, learning the latent space in a problem independent way makes it non trivial to initialize the tracking process by picking appropriate initial values for the latent variables, and thus for the pose. In this paper, the authors show that by directly using observable quantities as their latent variables, they eliminate this problem and achieve full automation given only modest amounts of training data.
- Format: PDF
- Size: 1294.1 KB