Abstract
Recent works on convolutional neural networks (CNNs) for facial alignment have demonstrated unprecedented accuracy on a variety of large, publicly available datasets. However, the developed models are often both cumbersome and computationally expensive, and are not adapted to applications on resource restricted devices. In this work, we look into developing and training compact facial alignment models that feature fast inference speed and small deployment size, making them suitable for applications on the aforementioned category of devices. Our main contribution lies in designing such small models while maintaining high accuracy of facial alignment. The models we propose make use of light CNN architectures adapted to the facial alignment problem for accurate two-stage prediction of facial landmark coordinates from low-resolution output heatmaps. We further combine the developed facial tracker with a rendering method, and build a real-time makeup try-on demo that runs client-side in smartphone Web browsers. More results and demo are in our project page: <a href="http://research.modiface.com/makeup-try-on-cvprw2019/">this http URL</a>
Abstract (translated)
最近的卷积神经网络（CNN）面部定位的研究表明，在各种大型的公开数据集上具有前所未有的准确性。然而，所开发的模型通常既繁琐又昂贵，并且不适合资源受限设备上的应用程序。在这项工作中，我们研究开发和训练具有快速推理速度和小部署尺寸的紧凑型面部对齐模型，使其适用于上述设备类别的应用。我们的主要贡献在于设计这样的小模型，同时保持高精度的面部定位。我们提出的模型利用光CNN结构来适应人脸对准问题，从而从低分辨率输出热图精确预测人脸地标坐标。我们进一步将开发的面部跟踪器与渲染方法结合起来，构建了一个在智能手机网络浏览器中运行客户端的实时化妆试镜。更多结果和演示在我们的项目页面中：<a href=“http://research.modifice.com/composition-try-on-cvprw2019/”>此http URL</a>
URL
https://arxiv.org/abs/1906.02260
