通过学习全局编辑方向与局部调整实现保持身份的多面部属性编辑
Identity-preserving Editing of Multiple Facial Attributes by Learning Global Edit Directions and Local Adjustments
AI总结：
本文提出 ID-Style，通过可学习全局方向与实例感知强度预测器实现多面部属性编辑，在网络规模减少约95%的同时显著提升身份保持与操控准确率。
摘要：
近年来，使用预训练生成对抗网络（GANs）进行语义面部属性编辑吸引了研究人员的大量关注与投入。由于 StyleGANs 生成的人脸图像质量很高，许多工作都聚焦于 StyleGANs 的潜空间以及所提出的面部图像编辑方法。尽管这些方法在操控用户指定属性方面取得了令人满意的结果，但它们尚未实现保持身份这一目标，而这是一项重要挑战。我们提出了 ID-Style，这是一种能够解决属性操控过程中身份丢失问题的新架构。ID-Style 的关键组件包括可学习全局方向（LGD）和实例感知强度预测器（IAIP）网络：前者为每个属性寻找一个共享且半稀疏的方向，后者根据输入实例对全局方向进行微调。此外，我们在训练过程中引入两种损失，以促使 LGD 找到半稀疏语义方向，并与 IAIP 一起保持输入实例的身份。尽管与同类先进工作相比网络规模减少了约 95%，但它在身份保持指标（FRS）和平均操控准确率（mACC）上分别比基线方法高出 10% 和 7%。
英文摘要：
Semantic facial attribute editing using pre-trained Generative Adversarial Networks (GANs) has attracted a great deal of attention and effort from researchers in recent years. Due to the high quality of face images generated by StyleGANs, much work has focused on the StyleGANs' latent space and the proposed methods for facial image editing. Although these methods have achieved satisfying results for manipulating user-intended attributes, they have not fulfilled the goal of preserving the identity, which is an important challenge. We present ID-Style, a new architecture capable of addressing the problem of identity loss during attribute manipulation. The key components of ID-Style include Learnable Global Direction (LGD), which finds a shared and semi-sparse direction for each attribute, and an Instance-Aware Intensity Predictor (IAIP) network, which finetunes the global direction according to the input instance. Furthermore, we introduce two losses during training to enforce the LGD to find semi-sparse semantic directions, which along with the IAIP, preserve the identity of the input instance. Despite reducing the size of the network by roughly 95% as compared to similar state-of-the-art works, it outperforms baselines by 10% and 7% in Identity preserving metric (FRS) and average accuracy of manipulation (mACC), respectively.
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。
