imGHUM

imGHUM is a generative model of 3D human shape and articulated pose, represented as a signed distance function. The full body is modeled implicitly as a function zero-level-set and without the use of an explicit template mesh. We compute the signed distance $s = S\left(\rho, \alpha\right)$ and the semantics $c = C\left(\rho, \alpha\right)$ of a spatial point $\rho$ to the surface of an articulated human shape defined by the generative latent code $\alpha$. Using an explicit skeleton, we transform the point $\rho$ into the normalized coordinate frames as {$\tilde{\rho}^{j}$} for $N = 4$ sub-part networks, modeling body, hands, and head. Each sub-model {$S^{j}$} represents a semantic signed-distance function. The sub-models are finally combined consistently using an MLP U to compute the outputs $s$ and $c$ for the full body. The multi-part pipeline builds a full body model as well as sub-part models for head and hands, jointly, in a consistent training loop.

On the right of the Figure, we visualize the zero-level-set body surface extracted with marching cubes and the implicit correspondences to a canonical instance given by the output semantics. The semantics allows e.g. for surface coloring or texturing.