基于人眼感知设计面部相似度度量，提升换脸匿名性与自然性平衡。
PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization
- 构建6400组三元组数据，学习人眼对人脸相似度的感知差异。
- 在相似度预测和属性分类任务上优于现有方法。
- 适合关注隐私保护与图像生成质量的研究者。
随着社会对隐私问题的关注增加，面部匿名化技术不断发展，包括将一人身份替换为另一人的换脸方法。在换脸中实现匿名性与自然性的平衡，需谨慎选择身份：过于相似会削弱匿名性，而差异过大则降低自然性。现有模型仅关注二元身份判断（是否同一人），难以衡量如‘完全不同’与‘高度相似但不同’等细微差异。本文提出一种基于人类感知的面部相似度度量方法，构建了包含6,400组三元组标注的数据集，并通过度量学习预测相似度。实验表明，该方法在面部相似度预测及基于属性的面部分类任务上均显著优于现有方法。
原文摘要 · Abstract (English)
In response to rising societal awareness of privacy concerns, face anonymization techniques have advanced, including the emergence of face-swapping methods that replace one identity with another. Achieving a balance between anonymity and naturalness in face swapping requires careful selection of identities: overly similar faces compromise anonymity, while dissimilar ones reduce naturalness. Existing models, however, focus on binary identity classification "the same person or not", making it difficult to measure nuanced similarities such as "completely different" versus "highly similar but different." This paper proposes a human-perception-based face similarity metric, creating a dataset of 6,400 triplet annotations and metric learning to predict the similarity. Experimental results demonstrate significant improvements in both face similarity prediction and attribute-based face classification tasks over existing methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。