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 provide qualitative results for dense human body
correspondence. We make our code available at this http URL
along with supplementary materials.

该研究提出了一种称为 DenseReg 的系统，使用手动标记的面部特征点作为训练网络的基础，实现了从图像到模板之间的密集对应关系，其在面部分析任务及身体对应分析中取得了较好的结果。