RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models

Understand

We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image.

• Existing methods fail to capture intricate details such as hairstyles which we tackle in this paper.
• We first identify an overlooked problem of catastrophic forgetting that arises when fitting triplanes sequentially on many avatars, caused by the MLP decoder sharing scheme.
• To overcome this issue, we raise a novel data scheduling strategy and a weight consolidation regularization term, which improves the decoder's capability of rendering sharper details.