Identity Preserving 3D Head Stylization with Multiview Score Distillation

Bahri Batuhan Bilecen, Ahmet Berke Gokmen, Furkan Guzelant, Aysegul Dundar

Bilkent University, Computer Science Department

Paper Code

Our method effectively balances stylization and identity preservation, whereas other approaches often struggle to achieve high-quality stylization, lack accurate identity retention, and suffer from generating identical faces for different inputs.

You may refresh the page to synchronize all visible videos.

Input

Joker

Pixar

Zombie

Statue

Werewolf

Sketch

Abstract

3D head stylization transforms realistic facial features into artistic representations, enhancing user engagement across applications such as gaming and virtual reality. While 3D-aware generators have made significant advancements, many 3D stylization methods primarily provide near-frontal views and struggle to preserve the unique identities of original subjects, often resulting in outputs that lack diversity and individuality. This paper addresses these challenges by leveraging the PanoHead model, which synthesizes images from a comprehensive 360-degree perspective. We propose a novel framework that employs negative log-likelihood distillation (LD) to enhance identity preservation and improve stylization quality. By integrating multi-view grid score and mirror gradients within the 3D GAN architecture and introducing a score rank weighing technique, our approach achieves substantial qualitative and quantitative improvements. Our findings not only advance the state of 3D head stylization but also provide valuable insights into effective distillation processes between diffusion models and GANs, focusing on the critical issue of identity preservation.