arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.01237cs.CV
收藏

面部去风格化

Face Destylization

Australian National University(澳大利亚国立大学);Data61/CSIRO(Data61/澳大利亚联邦科学与工业研究组织)

Fatemeh Shiri, Xin Yu, Fatih Porikli, Piotr Koniusz

摘要:

到目前为止,已经提出了许多产生肖像艺术风格的风格转移方法。然而,将风格化的肖像转换回现实面孔的逆问题还有待深入研究。将艺术肖像还原为原始照片般逼真的人脸图像具有促进人类感知和身份分析的潜力。在本文中,我们提出了一种新的人脸去风格化神经网络(FDNN)从风格化的恢复潜在的照片级真实感的脸。我们开发了一个由卷积层、全连接层和去卷积层组成的风格去除网络。卷积层被设计为从风格化的面部图像中提取面部成分。相应地,全连接层将提取的风格化图像的特征图转换为对应的真实面部的特征图,并且解卷积层从转换的特征图生成真实面部。为了使去风格化的人脸与真实的人脸图像相似,我们采用了一个判别网络,该网络由卷积层和全连接层组成。我们通过对大量合成图像进行实验来证明我们的网络的有效性。此外,我们证明了我们的网络可以从风格化的肖像和真实的绘画中恢复人脸,而在训练阶段无法获得风格化的数据。

英文摘要:

Numerous style transfer methods which produce artistic styles of portraits have been proposed to date. However, the inverse problem of converting the stylized portraits back into realistic faces is yet to be investigated thoroughly. Reverting an artistic portrait to its original photo-realistic face image has potential to facilitate human perception and identity analysis. In this paper, we propose a novel Face Destylization Neural Network (FDNN) to restore the latent photo-realistic faces from the stylized ones. We develop a Style Removal Network composed of convolutional, fully-connected and deconvolutional layers. The convolutional layers are designed to extract facial components from stylized face images. Consecutively, the fully-connected layer transfers the extracted feature maps of stylized images into the corresponding feature maps of real faces and the deconvolutional layers generate real faces from the transferred feature maps. To enforce the destylized faces to be similar to authentic face images, we employ a discriminative network, which consists of convolutional and fully connected layers. We demonstrate the effectiveness of our network by conducting experiments on an extensive set of synthetic images. Furthermore, we illustrate our network can recover faces from stylized portraits and real paintings for which the stylized data was unavailable during the training phase.

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。

↑