AHS通过合成数据增强实现更自然的头像替换，适应多样姿态与表情。
AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
- 引入新型头像重演合成数据增强，提升模型泛化能力。
- 无需成对数据，在真实场景下保持身份与表情一致性。
- 擅长处理夸张表情和复杂发型，适合高难度头像融合任务。
近期数字媒体技术的发展催生了对复杂人像编辑技术的日益增长需求，尤其是头像替换——将一个人的头部无缝融合到另一个人的身体上。然而，现有方法主要依赖以面部为中心的裁剪数据，视角有限，严重限制了其在现实场景中的应用。它们在应对多变的表情、发型及面部区域外的自然融合方面表现不佳。为此，我们提出自适应头像合成（AHS），能有效处理包含不同头部姿态和表情的完整上身图像。AHS采用一种新颖的头像重演合成数据增强策略，克服自监督训练的局限性，提升了在无配对数据情况下对多样表情和朝向的泛化能力。全面实验表明，AHS在挑战性真实场景中表现卓越，生成结果视觉连贯，保留身份与表情真实性，适用于各种头部姿态和发型。尤其在剧烈表情变化和显著头部姿态变动时，仍能忠实保持面部身份与配饰特征。
原文摘要 · Abstract (English)
Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping, where one's head is seamlessly integrated with another's body. However, current approaches predominantly rely on face-centered cropped data with limited view angles, significantly restricting their real-world applicability. They struggle with diverse head expressions, varying hairstyles, and natural blending beyond facial regions. To address these limitations, we propose Adaptive Head Synthesis (AHS), which effectively handles full upper-body images with varied head poses and expressions. AHS incorporates a novel head reenacted synthetic data augmentation strategy to overcome self-supervised training constraints, enhancing generalization across diverse facial expressions and orientations without requiring paired training data. Comprehensive experiments demonstrate that AHS achieves superior performance in challenging real-world scenarios, producing visually coherent results that preserve identity and expression fidelity across various head orientations and hairstyles. Notably, AHS shows exceptional robustness in maintaining facial identity while drastic expression changes and faithfully preserving accessories while significant head pose variations.
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。