论文标题
3D卡通面部生成具有单个gan图像的可控表达式
3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image
论文作者
论文摘要
在本文中，我们调查了一项开放的研究任务，该任务是从单个2D GAN产生人体面部且没有3D监督的3D卡通脸部形状，在那里我们还可以操纵3D形状的面部表情。为此，我们发现了stylegan潜在空间的语义含义，因此我们能够通过控制潜在代码来产生各种表达式，姿势和照明条件的面部图像。具体来说，我们首先对卡通数据集上预验证的Stylegan脸部模型进行了修复。通过将相同的潜在代码喂入面部和卡通生成模型，我们的目标是实现从2D人脸图像到卡通风格的化身的翻译。然后，我们发现了甘恩潜在空间的语义方向，以试图在保留原始身份的同时改变面部表情。由于我们没有任何针对卡通面的3D注释，因此我们操纵潜在代码以生成具有不同姿势和照明条件的图像，以便我们可以重建3D卡通脸部形状。我们在定性和定量上验证了方法在三个卡通数据集上的疗效。
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.
