U-Face: An Efficient and Generalizable Framework for Unsupervised Facial Attribute Editing via Subspace Learning

2026-03-14

AI Summary

This work addresses the limited disentanglement in existing unsupervised facial attribute editing methods, which often leads to interference among attributes. To enhance attribute disentanglement, the authors formulate semantic vector learning as a low-dimensional semantic subspace learning problem and propose an autoencoder framework that incorporates semantic directions and attribute boundary vectors under orthogonal non-negative constraints. Furthermore, they design an alternating iterative optimization algorithm (AIDC) with closed-form updates and convergence guarantees. Without requiring labeled data, the method achieves high-precision, continuous, and identity-preserving facial attribute editing, significantly improving both disentanglement and generalization performance.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Adversarial Attacks & Robustness
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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.

Problem

• unsupervised facial attribute editing
• disentanglement
• controllability
• latent space
• semantic manipulation

Innovation

• subspace learning
• unsupervised facial attribute editing
• disentangled representation
• orthogonal non-negative constraints
• alternating iterative optimization