ArtNeRF: A Stylized Neural Field for 3D-Aware Cartoonized Face Synthesis

TL;DR

ArtNeRF introduces a novel 3D-aware face stylization framework that enables high-quality, real-time cartoon face synthesis with arbitrary styles, leveraging style embeddings, adaptive blending, and neural rendering.

Contribution

It presents a new framework combining style encoding, adaptive style blending, and neural rendering for 3D-aware cartoon face synthesis, addressing previous limitations.

Findings

Generates high-quality 3D-aware cartoon faces with arbitrary styles.

Achieves real-time rendering at higher resolutions.

Demonstrates versatility and robustness across diverse styles.

Abstract

Recent advances in generative visual models and neural radiance fields have greatly boosted 3D-aware image synthesis and stylization tasks. However, previous NeRF-based work is limited to single scene stylization, training a model to generate 3D-aware cartoon faces with arbitrary styles remains unsolved. We propose ArtNeRF, a novel face stylization framework derived from 3D-aware GAN to tackle this problem. In this framework, we utilize an expressive generator to synthesize stylized faces and a triple-branch discriminator module to improve the visual quality and style consistency of the generated faces. Specifically, a style encoder based on contrastive learning is leveraged to extract robust low-dimensional embeddings of style images, empowering the generator with the knowledge of various styles. To smooth the training process of cross-domain transfer learning, we propose an adaptive style blending module which helps inject style information and allows users to freely tune the level of stylization. We further introduce a neural rendering module to achieve efficient real-time rendering of images with higher resolutions. Extensive experiments demonstrate that ArtNeRF is versatile in generating high-quality 3D-aware cartoon faces with arbitrary styles.