arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.11079cs.CVcs.AIcs.GR
收藏

ReenactGAN:通过边界迁移学习再现人脸

ReenactGAN: Learning to Reenact Faces via Boundary Transfer

SenseTime Research(商汤科技研究院);Nanyang Technological University(南洋理工大学)

Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, Chen Change Loy

摘要:

我们提出了一个新的基于学习的框架,面对重演。该方法被称为ReenactGAN,能够将面部运动和表情从任意人的单目视频输入传输到目标人。而不是在像素空间中执行直接传输,这可能会导致结构性伪影,我们首先将源面映射到边界潜在空间。随后使用Transformer来使源面的边界适应目标面的边界。最后,使用目标特定的解码器来生成再现的目标面部。由于有效和可靠的基于边界的转移,我们的方法可以执行照片般真实的人脸再现。此外,ReenactGAN的吸引力在于整个重演过程是纯粹的前馈,因此重演过程可以实时运行(在一个GTX 1080 GPU上为30 FPS)。数据集和模型将在https://wywu.github.io/projects/ReenactGAN/ReenactGAN.html上公开提供

英文摘要:

We present a novel learning-based framework for face reenactment. The proposed method, known as ReenactGAN, is capable of transferring facial movements and expressions from monocular video input of an arbitrary person to a target person. Instead of performing a direct transfer in the pixel space, which could result in structural artifacts, we first map the source face onto a boundary latent space. A transformer is subsequently used to adapt the boundary of source face to the boundary of target face. Finally, a target-specific decoder is used to generate the reenacted target face. Thanks to the effective and reliable boundary-based transfer, our method can perform photo-realistic face reenactment. In addition, ReenactGAN is appealing in that the whole reenactment process is purely feed-forward, and thus the reenactment process can run in real-time (30 FPS on one GTX 1080 GPU). Dataset and model will be publicly available at https://wywu.github.io/projects/ReenactGAN/ReenactGAN.html

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。

↑