解耦种族表型：种族相关面部表型特征的细粒度控制
Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics
AI总结：
本文提出一种新颖GAN框架，通过解耦潜在空间实现对面部图像中种族相关表型属性的细粒度控制，并引入基于CelebA-HQ的高质量多样化2D面部数据集，仅依赖2D图像即可达到最先进的个体控制效果。
摘要：
在保持面部身份的同时，对2D面部图像实现有效的细粒度外观变化是一项具有挑战性的任务，因为常见的2D面部特征编码空间具有高度复杂性和纠缠性。尽管存在这些挑战，通过解耦实现的这种细粒度控制，对于多个自动化面部分析任务中数据驱动的种族偏见缓解策略而言是一个关键推动因素，因为它允许分析、表征和合成人类面部多样性。在本文中，我们提出了一种新颖的GAN框架，以实现对面部图像中个体种族相关表型属性的细粒度控制。我们的框架将潜在（特征）空间分解为与种族相关面部表型表示相对应的元素，从而分离表型方面（例如皮肤、头发颜色、鼻子、眼睛、嘴巴形状），这些方面在现实世界面部数据中极难进行稳健标注。同时，我们还引入了一个从CelebA-HQ中提取的高质量增强、多样化的2D面部图像数据集，用于GAN训练。与先前的工作不同，我们的框架仅依赖2D图像及相关参数，即可实现对种族相关表型属性的最先进个体控制，并具有改进的照片级真实感输出。
英文摘要：
Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these challenges, such fine-grained control, by way of disentanglement is a crucial enabler for data-driven racial bias mitigation strategies across multiple automated facial analysis tasks, as it allows to analyse, characterise and synthesise human facial diversity. In this paper, we propose a novel GAN framework to enable fine-grained control over individual race-related phenotype attributes of the facial images. Our framework factors the latent (feature) space into elements that correspond to race-related facial phenotype representations, thereby separating phenotype aspects (e.g. skin, hair colour, nose, eye, mouth shapes), which are notoriously difficult to annotate robustly in real-world facial data. Concurrently, we also introduce a high quality augmented, diverse 2D face image dataset drawn from CelebA-HQ for GAN training. Unlike prior work, our framework only relies upon 2D imagery and related parameters to achieve state-of-the-art individual control over race-related phenotype attributes with improved photo-realistic output.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
