arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.12445cs.CVeess.IV
收藏

用于卡通人脸生成的微调StyleGAN2

Fine-Tuning StyleGAN2 For Cartoon Face Generation

Seoul National University(首尔国立大学)

Jihye Back

摘要:

最近的研究表明,在无监督的图像到图像(I2 I)的翻译显着的成功。然而,由于数据的不平衡性,学习各个领域的联合分布仍然非常具有挑战性。现有的模型虽然能够生成逼真的目标图像,但很难保持源图像的结构。此外,在多个领域的大数据上训练生成模型需要大量的时间和计算机资源。为了解决这些限制,我们提出了一种新的图像到图像的翻译方法,通过微调stylegan 2预训练模型来生成目标域的图像。stylegan 2模型适用于不平衡数据集上的无监督I2 I翻译;它高度稳定,生成逼真的图像,甚至在应用简单的微调技术时可以从有限的数据中正确学习。因此,在本文中,我们提出了新的方法来保持源图像的结构,并在目标域中生成逼真的图像。代码和结果可在https://github.com/happy-jihye/Cartoon-StyleGan2上获得

英文摘要:

Recent studies have shown remarkable success in the unsupervised image to image (I2I) translation. However, due to the imbalance in the data, learning joint distribution for various domains is still very challenging. Although existing models can generate realistic target images, it's difficult to maintain the structure of the source image. In addition, training a generative model on large data in multiple domains requires a lot of time and computer resources. To address these limitations, we propose a novel image-to-image translation method that generates images of the target domain by finetuning a stylegan2 pretrained model. The stylegan2 model is suitable for unsupervised I2I translation on unbalanced datasets; it is highly stable, produces realistic images, and even learns properly from limited data when applied with simple fine-tuning techniques. Thus, in this paper, we propose new methods to preserve the structure of the source images and generate realistic images in the target domain. The code and results are available at https://github.com/happy-jihye/Cartoon-StyleGan2

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑