论文标题
与生成对抗网络的逼真的头发合成
Realistic Hair Synthesis with Generative Adversarial Networks
论文作者
论文摘要
生成建模的最新成功加速了对该主题的研究，并引起了研究人员的注意。用于实现这一成功的最重要方法之一是生成对抗网络（GAN）。它有许多应用领域，例如；虚拟现实（VR），增强现实（AR），超级分辨率，图像增强。尽管使用深度学习和生成性建模最近在头发合成和风格转移方面取得了进步，但由于头发的复杂性，仍然包含未解决的挑战。文献中提出的解决此问题的方法通常集中于对图像进行高质量的头发编辑。在本文中，提出了一种生成的对抗网络方法来解决头发合成问题。在开发这种方法的同时，它的目的是实现实时头发合成，同时实现与文献中最佳方法竞争的视觉输出。提出的方法是使用FFHQ数据集训练的，然后评估了其发型转移和头发重建任务的结果。将这些任务和方法的运行时间获得的结果与文献中最好的方法之一进行了比较。比较以128x128的分辨率进行。进行了比较的结果，已经表明，所提出的方法在逼真的头发合成方面与密歇根州取得了竞争性结果，并且在运营时间方面的表现更好。
Recent successes in generative modeling have accelerated studies on this subject and attracted the attention of researchers. One of the most important methods used to achieve this success is Generative Adversarial Networks (GANs). It has many application areas such as; virtual reality (VR), augmented reality (AR), super resolution, image enhancement. Despite the recent advances in hair synthesis and style transfer using deep learning and generative modelling, due to the complex nature of hair still contains unsolved challenges. The methods proposed in the literature to solve this problem generally focus on making high-quality hair edits on images. In this thesis, a generative adversarial network method is proposed to solve the hair synthesis problem. While developing this method, it is aimed to achieve real-time hair synthesis while achieving visual outputs that compete with the best methods in the literature. The proposed method was trained with the FFHQ dataset and then its results in hair style transfer and hair reconstruction tasks were evaluated. The results obtained in these tasks and the operating time of the method were compared with MichiGAN, one of the best methods in the literature. The comparison was made at a resolution of 128x128. As a result of the comparison, it has been shown that the proposed method achieves competitive results with MichiGAN in terms of realistic hair synthesis, and performs better in terms of operating time.
