We propose Semantic Facial Feature Control (SeFFeC) - a novel method for
fine-grained face shape editing. Our method enables the manipulation of
human-understandable, semantic face features, such as nose length or mouth
width, which are defined by different groups of facial landmarks. In contrast
to existing methods, the use of facial landmarks enables precise measurement of
the facial features, which then enables training SeFFeC without any manually
annotated labels. SeFFeC consists of a transformer-based encoder network that
takes a latent vector of a pre-trained generative model and a facial feature
embedding as input, and learns to modify the latent vector to perform the
desired face edit operation. To ensure that the desired feature measurement is
changed towards the target value without altering uncorrelated features, we
introduced a novel semantic face feature loss. Qualitative and quantitative
results show that SeFFeC enables precise and fine-grained control of 23 facial
features, some of which could not previously be controlled by other methods,
without requiring manual annotations. Unlike existing methods, SeFFeC also
provides deterministic control over the exact values of the facial features and
more localised and disentangled face edits.

我们提出了一种新颖的方法 Semantic Facial Feature Control (SeFFeC) 用于细粒度人脸形状编辑，该方法能够操纵人类可理解的语义人脸特征，并且由不同组的面部标志定义，通过使用面部标志进行精确测量从而实现对 SeFFeC 进行无需手动注释的训练。SeFFeC 由基于 Transformer 的编码网络组成，接受预训练生成模型的潜在向量和面部特征嵌入作为输入，并学习修改潜在向量以执行期望的面部编辑操作。通过引入新颖的语义人脸特征损失，以确保将期望的特征测量改变为目标值，而不会改变不相关的特征。定性和定量实验结果表明，SeFFeC 能够对 23 个面部特征进行精确和细粒度的控制，其中一些特征以前无法通过其他方法进行控制，而无需手动注释。与现有方法不同，SeFFeC 还提供了对面部特征的确切值的确定性控制，以及更局部化和解耦的面部编辑。