CVJul 29, 2022

3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image

arXiv:2207.14425v26 citationsh-index: 87
Originality Incremental advance
AI Analysis

This addresses the problem of creating expressive 3D avatars for applications like gaming or virtual reality, but it is incremental as it builds on existing StyleGAN techniques.

The paper tackles generating 3D cartoon face shapes from single 2D GAN-generated human faces without 3D supervision, enabling controllable facial expressions, and validates the method on three cartoon datasets with qualitative and quantitative results.

In this paper, we investigate an open research task of generating 3D cartoon face shapes from single 2D GAN generated human faces and without 3D supervision, where we can also manipulate the facial expressions of the 3D shapes. To this end, we discover the semantic meanings of StyleGAN latent space, such that we are able to produce face images of various expressions, poses, and lighting conditions by controlling the latent codes. Specifically, we first finetune the pretrained StyleGAN face model on the cartoon datasets. By feeding the same latent codes to face and cartoon generation models, we aim to realize the translation from 2D human face images to cartoon styled avatars. We then discover semantic directions of the GAN latent space, in an attempt to change the facial expressions while preserving the original identity. As we do not have any 3D annotations for cartoon faces, we manipulate the latent codes to generate images with different poses and lighting conditions, such that we can reconstruct the 3D cartoon face shapes. We validate the efficacy of our method on three cartoon datasets qualitatively and quantitatively.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes