U-Face: 一种高效的、可泛化的基于子空间学习的无监督面部属性编辑框架
U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning
AI总结：
本文提出U-Face框架，通过子空间学习方法解决无监督面部属性编辑中的解耦难题，引入正交非负约束和属性边界向量提升控制能力，采用AIDC算法实现高效优化。
摘要：
基于潜在空间的面部属性编辑方法在数字娱乐、虚拟人创建和人机交互系统中广泛应用，因其在连续编辑方面的高效性和灵活性。其中，无监督潜在空间方法通过发现有效的语义向量而不依赖标注数据，受到研究社区的广泛关注。然而，现有方法在解耦方面仍存在困难，因为操控特定面部属性可能无意中影响其他属性，使精细控制变得复杂。为解决这些问题，我们提出了一种新的框架，称为无监督面部属性可控编辑（U-Face），旨在提供一种有效的、可适应的无监督面部属性编辑解决方案。该方法将语义向量学习框架为一个子空间学习问题，其中潜在向量被近似为由语义向量矩阵张成的低维语义子空间内。这种表征也可以等价地从投影-重建视角进行解释，并进一步推广到自编码器框架中，为以灵活的方式支持解耦表示学习提供了基础。为了提高解耦性和可控性，我们对语义向量施加正交非负约束，并结合属性边界向量以减少学习方向中的耦合。尽管这些约束使优化问题具有挑战性，我们设计了一个交替迭代算法，称为交替迭代解耦和可控性（AIDC），具有闭式更新和在特定条件下可证明收敛性。
英文摘要：
Latent space-based facial attribute editing methods have gained popularity in applications such as digital entertainment, virtual avatar creation, and human-computer interaction systems due to their potential for efficient and flexible attribute manipulation, particularly for continuous edits. Among these, unsupervised latent space-based methods, which discover effective semantic vectors without relying on labeled data, have attracted considerable attention in the research community. However, existing methods still encounter difficulties in disentanglement, as manipulating a specific facial attribute may unintentionally affect other attributes, complicating fine-grained controllability. To address these challenges, we propose a novel framework designed to offer an effective and adaptable solution for unsupervised facial attribute editing, called Unsupervised Facial Attribute Controllable Editing (U-Face). The proposed method frames semantic vector learning as a subspace learning problem, where latent vectors are approximated within a lower-dimensional semantic subspace spanned by a semantic vector matrix. This formulation can also be equivalently interpreted from a projection-reconstruction perspective and further generalized into an autoencoder framework, providing a foundation that can support disentangled representation learning in a flexible manner. To improve disentanglement and controllability, we impose orthogonal non-negative constraints on the semantic vectors and incorporate attribute boundary vectors to reduce entanglement in the learned directions. Although these constraints make the optimization problem challenging, we design an alternating iterative algorithm, called Alternating Iterative Disentanglement and Controllability (AIDC), with closed-form updates and provable convergence under specific conditions.
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。
