Everyday, we are bombarded with many photographs of faces, whether on social media, television, or smartphones. From an evolutionary perspective, faces are intended to be remembered, mainly due to survival and personal relevance. However, all these faces do not have the equal opportunity to stick in our minds. It has been shown that memorability is an intrinsic feature of an image but yet, it is largely unknown what attributes make an image more memorable. In this work, we aimed to address this question by proposing a fast approach to modify and control the memorability of face images. In our proposed method, we first found a hyperplane in the latent space of StyleGAN to separate high and low memorable images. We then modified the image memorability (while maintaining the identity and other facial features such as age, emotion, etc.) by moving in the positive or negative direction of this hyperplane normal vector. We further analyzed how different layers of the StyleGAN augmented latent space contribute to face memorability. These analyses showed how each individual face attribute makes an image more or less memorable. Most importantly, we evaluated our proposed method for both real and synthesized face images. The proposed method successfully modifies and controls the memorability of real human faces as well as unreal synthesized faces. Our proposed method can be employed in photograph editing applications for social media, learning aids, or advertisement purposes.
Facial recognition technology and human raters can predict political orientation from images of expressionless faces even when controlling for demographics and self-presentation
Center for Research on Intelligent Perception and Computing, NLPR, CASIA（中国科学院自动化研究所模式识别国家重点实验室智能感知与计算研究中心）；University of Chinese Academy of Sciences（中国科学院大学）；Meituandianping Group（美团点评集团）；Artificial Intelligence Research, CAS（中国科学院人工智能研究院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
近年来，人脸肖像编辑技术取得了很大的进步。然而，先前的方法或者1）对预定义的面部属性进行操作，缺乏控制高级语义面部组件的形状的灵活性（例如，眼睛、鼻子、嘴巴），或者2）将手动编辑的遮罩或草图作为可观察变化的中间表示，但是这样的附加输入通常需要额外的努力来获得。为了打破现有方法的局限性（例如形状、遮罩或草图），我们提出了一种新的框架r-FACE（Reference-guided FACE Component Editing），用于进行具有几何变化的多样化和可控的面组件编辑。具体而言，r-FACE以图像修补模型为主干，利用基准图像作为控制面部成分的形状的条件。为了鼓励框架集中在目标人脸组件，一个例子引导的注意力模块被设计为融合注意力特征和目标人脸组件特征提取的参考图像。通过大量的实验验证和比较，我们验证了所提出的框架的有效性。
3D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Prior
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
LARNet: Lie Algebra Residual Network for Face Recognition
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Data Platform（腾讯数据平台）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
University of Parma, Department of Engineering and Architecture（帕尔马大学工程与建筑系）；University of Siena, Department of Information Engineering and Mathematical Sciences（锡耶纳大学信息工程与数学科学系）
High Fidelity Face Manipulation with Extreme Poses and Expressions
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Research on Intelligent Perception and Computing, CASIA（中国科学院自动化研究所智能感知与计算研究中心）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Horizon Robotics（地平线机器人）；Tsinghua University（清华大学）
Learning an Animatable Detailed 3D Face Model from In-The-Wild Images
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Max Planck ETH Center for Learning System（马克斯·普朗克-苏黎世联邦理工学院学习系统中心）
虽然目前的单目3D人脸重建方法可以恢复精细的几何细节，他们受到一些限制。某些方法生成的面无法真实地设置动画，因为它们没有对皱纹如何随表情变化进行建模。其他方法是在高质量的面部扫描上训练的，并且不能很好地推广到野外图像。我们提出了第一种方法，回归3D人脸形状和动画的细节，是特定于个人，但随着表情的变化。我们的模型DECA（Detailed Expression Capture and Animation）经过训练，可以从由特定于人的细节参数和通用表情参数组成的低维潜在表示中稳健地生成UV位移图，而回归量则经过训练，可以从单个图像中预测细节，形状，表情，姿势和照明参数。为了实现这一点，我们引入了一种新的细节一致性损失，从依赖于表情的皱纹中分离出特定于人的细节。这种解开使我们能够通过控制表情参数，同时保持个人特定细节不变，来合成逼真的个人特定皱纹。DECA是从野外图像中学习的，没有配对的3D监督，并在两个基准上实现了最先进的形状重建精度。在野外数据的定性结果表明，DECA的鲁棒性和它的能力，解开身份和表情相关的细节，使动画重建的脸。该模型和代码可在https://deca.is.tue.mpg.de上公开获得。
Towards Consistent and Controllable Image Synthesis for Face Editing
Center for Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu（机器视觉与信号分析中心，信息科技与电气工程学院，奥卢大学）；Key Laboratory of Child Development and Learning Science of Ministry of Education, School of Biological Sciences and Medical Engineering, Southeast University（教育部儿童发展与学习科学重点实验室，生物科学与医学工程学院，东南大学）
