Fu Yuanbin, Ma Jiayi, Guo Xiaojie
College of Intelligence and Computing, Tianjin University, Tianjin 300350, China.
Electronic Information School, Wuhan University, Wuhan 430072, China.
Entropy (Basel). 2021 May 16;23(5):615. doi: 10.3390/e23050615.
In the context of social media, large amounts of headshot photos are taken everyday. Unfortunately, in addition to laborious editing and modification, creating a visually compelling photographic masterpiece for sharing requires advanced professional skills, which are difficult for ordinary Internet users. Though there are many algorithms automatically and globally transferring the style from one image to another, they fail to respect the semantics of the scene and are unable to allow users to merely transfer the attributes of one or two face organs in the foreground region leaving the background region unchanged. To overcome this problem, we developed a novel framework for semantically meaningful local face attribute transfer, which can flexibly transfer the local attribute of a face organ from the reference image to a semantically equivalent organ in the input image, while preserving the background. Our method involves warping the reference photo to match the shape, pose, location, and expression of the input image. The fusion of the warped reference image and input image is then taken as the initialized image for a neural style transfer algorithm. Our method achieves better performance in terms of inception score (3.81) and Fréchet inception distance (80.31), which is about 10% higher than those of competitors, indicating that our framework is capable of producing high-quality and photorealistic attribute transfer results. Both theoretical findings and experimental results are provided to demonstrate the efficacy of the proposed framework, reveal its superiority over other state-of-the-art alternatives.
在社交媒体的背景下，每天都会拍摄大量的头像照片。不幸的是，除了费力的编辑和修改之外，要创作一幅引人注目的用于分享的摄影杰作需要先进的专业技能，而这对于普通互联网用户来说是困难的。尽管有许多算法可以自动且全局地将一种图像的风格转移到另一种图像上，但它们没有考虑场景的语义，也无法让用户仅转移前景区域中一两个面部器官的属性而保持背景区域不变。为了克服这个问题，我们开发了一种用于语义有意义的局部面部属性转移的新颖框架，它可以灵活地将面部器官的局部属性从参考图像转移到输入图像中语义等效的器官上，同时保留背景。我们的方法包括对参考照片进行变形，以匹配输入图像的形状、姿势、位置和表情。然后将变形后的参考图像与输入图像融合，作为神经风格转移算法的初始化图像。我们的方法在 inception 分数（3.81）和 Fréchet inception 距离（80.31）方面取得了更好的性能，比竞争对手高出约 10%，这表明我们的框架能够产生高质量和逼真的属性转移结果。提供了理论发现和实验结果，以证明所提出框架的有效性，揭示其相对于其他现有最先进替代方案的优越性。
