Learning Neural Parametric Head Models

Figure 1 . We propose to learn a neural parametric head model based on neural fields: first, we capture a large dataset of over 5200 highfidelity head scans with varying shapes and expressions (left). We then non-rigidly register these scans to generate our training data. As a result of training, we obtain a disentangled latent that spans the space of shapes z id and expressions z ex (middle). At inference time, we can leverage the prior of our learned representation by fitting our model to a sparse input point cloud by solving for the latent codes (right).