Our model accepts 2D and 3D data for constructing the sphere face models. Extensive experiments show that SFM has high representation ability and clustering performance in its shape parameter space.

While discussing a past experiment on visualizing population data on a sphere's surface with another LLM enthusiast, they wondered whether this approach could be adapted for visualizing embeddings.

3D morphable models (3DMMs) are generative models for face shape and appearance. Recent works impose face recognition constraints on 3DMM shape parameters so that the face shapes of the same person ...