Stratified Avatar Generation from Sparse Observations

Ant Group Project website: https://fhan235.github.io/SAGENet/ (a) Sparse Observation (b) Disentangled Body (c) Upper-Body Recon. (d) Lower-Body Recon. (e) Full-Body Recon. Figure 1. Stratified avatar generation from sparse observations. Given the sensory sparse observation of the body motion: 6-DoF poses of the head and hand marked by RGB axes in (a), our method leverages a disentangled body representation in (b) to reconstruct the upper-body conditioned on the sparse observation in (c), and lower-body conditioned on the upper-body reconstruction in (d) to accomplish the full-body reconstruction in (e).