With the popularity of social media platforms such as Instagram and TikTok,
and the widespread availability and convenience of retouching tools, an
increasing number of individuals are utilizing these tools to beautify their
facial photographs. This poses challenges for fields that place high demands on
the authenticity of photographs, such as identity verification and social
media. By altering facial images, users can easily create deceptive images,
leading to the dissemination of false information. This may pose challenges to
the reliability of identity verification systems and social media, and even
lead to online fraud. To address this issue, some work has proposed makeup
removal methods, but they still lack the ability to restore images involving
geometric deformations caused by retouching. To tackle the problem of facial
retouching restoration, we propose a framework, dubbed Face2Face, which
consists of three components: a facial retouching detector, an image
restoration model named FaceR, and a color correction module called
Hierarchical Adaptive Instance Normalization (H-AdaIN). Firstly, the facial
retouching detector predicts a retouching label containing three integers,
indicating the retouching methods and their corresponding degrees. Then FaceR
restores the retouched image based on the predicted retouching label. Finally,
H-AdaIN is applied to address the issue of color shift arising from diffusion
models. Extensive experiments demonstrate the effectiveness of our framework
and each module.

通过提出的 Face2Face 框架，包括面部修饰检测器、基于预测修饰标签的图像修复模型 FaceR 和用于处理扩散模型引起的色彩偏移的分层自适应实例归一化（H-AdaIN）模块，来解决面部修饰还原问题，并通过实验验证了我们的框架和每个模块的有效性。

Face2Face：基于标签的面部修饰恢复

Face2Face: Label-driven Facial Retouching Restoration

Kinship verification using facial photographs captured in the wild is
difficult area of research in the science of computer vision. It might be used
for a variety of applications, including image annotation and searching for
missing children, etc. The largest challenge to kinship verification in
practice is the fact that parent and child photos frequently differ
significantly from one another. How to effectively respond to such a challenge
is important improving the efficiency of kinship verification. For this
purpose, we introduce a system to check relatedness that starts with a pair of
face images of a child and a parent, after which it is revealed whether two
people are related or not. The first step in our approach is face preprocessing
with two methods, a Retinex filter and an ellipse mask, then a feature
extraction step based on hist-Gabor wavelets, which is used before an efficient
dimensionality reduction method called TXQDA. Finally, determine if there is a
relationship. By using Cornell KinFace benchmark database, we ran a number of
tests to show the efficacy of our strategy. Our findings show that, in
comparison to other strategies currently in use, our system is robust.

使用野外拍摄的面部照片进行亲属关系验证是计算机视觉科学中的研究难点之一，本研究介绍了一个基于面部图像的亲属相关性检查系统，通过面部预处理、特征提取和降维等方法，有效地提高了亲属关系验证的效率。