arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.01876cs.CV
收藏

DeepFace:使用深度学习生成人脸

DeepFace: Face Generation using Deep Learning

Hardie Cate, Fahim Dalvi, Zeshan Hussain

摘要:

我们使用CNN来构建一个系统,该系统既可以根据各种不同的面部属性对面部图像进行分类,又可以根据一组所需的面部特征生成新的面部。在第一节中介绍了这个问题并提供了上下文之后,我们将在第二节中讨论与图像生成相关的最新工作。在第3节中,我们描述了用于微调CNN的方法,并使用受高斯混合模型启发的新方法生成新图像。在第4节中,我们讨论了我们的工作数据集,并描述了我们的预处理步骤和面部属性的处理。最后,在第5、6和7节中,我们解释了我们的实验和结果,并在下一节中得出结论。我们的分类系统具有82%的测试准确率。此外,我们的生成管道成功地创建了形状良好的面。

英文摘要:

We use CNNs to build a system that both classifies images of faces based on a variety of different facial attributes and generates new faces given a set of desired facial characteristics. After introducing the problem and providing context in the first section, we discuss recent work related to image generation in Section 2. In Section 3, we describe the methods used to fine-tune our CNN and generate new images using a novel approach inspired by a Gaussian mixture model. In Section 4, we discuss our working dataset and describe our preprocessing steps and handling of facial attributes. Finally, in Sections 5, 6 and 7, we explain our experiments and results and conclude in the following section. Our classification system has 82\% test accuracy. Furthermore, our generation pipeline successfully creates well-formed faces.

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。

↑