DenseReg：实际环境中，全卷积密集形状回归。 CVPR 2017 ，DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild. CVPR 2017。
摘要：在本文中，我们提出通过完全卷积网络学习从图像像素到密集模板网格的映射。我们将此任务作为一个回归问题，并利用手动注释的面部标注来训练我们的网络。我们使用这样的标注，在三维对象模板和输入图像之间，建立密集的对应领域，然后作为训练我们的回归系统的基础。我们表明，我们可以将来自语义分割的想法与回归网络相结合，产生高精度的“量化回归”架构。
我们的系统叫DenseReg，可以让我们以全卷积的方式估计密集的图像到模板的对应关系。因此，我们的网络可以提供有用的对应信息，而当用作统计可变形模型的初始化时，我们获得了标志性的本地化结果，远远超过当前最具挑战性的300W基准的最新技术。我们对大量面部分析任务的方法进行了全面评估，并且还展示了其用于其他估计任务的用途，如人耳建模。
In this paper we propose to learn a mapping from image pixels into a dense template grid through a fully convolutional network. We formulate this task as a regression problem and train our network by leveraging upon manually annotated facial landmarks “in-the-wild”. We use such landmarks to establish a dense correspondence field between a three-dimensional object template and the input image, which then serves as the ground-truth for training our regression system. We show that we can combine ideas from semantic segmentation with regression networks, yielding a highly-accurate ‘quantized regression’ architecture.
Our system, called DenseReg allows us to estimate dense image-to-template correspondences in a fully convolutional manner. As such our network can provide useful correspondence information as a stand-alone system, while when used as an initialization for Statistical Deformable Models we obtain landmark localization results that largely outperform the current state-of-the-art on the challenging 300W benchmark. We thoroughly evaluate our method on a host of facial analysis tasks, and also demonstrate its use for other correspondence estimation tasks, such as modelling of the human ear.
链接：
http://alpguler.com/DenseReg.html
原文链接：
https://m.weibo.cn/5501429448/4134165160734539
