AHS：通过合成数据增强的自适应头部合成
AHS: Adaptive Head Synthesis via Synthetic Data Augmentations
提出头部重演合成数据增强策略，在无配对数据下提升头部交换模型对多样表情、姿态和发型的泛化能力，可复用于其他需要跨身份属性迁移的编辑任务。
原文依据 AHS incorporates a novel head reenacted synthetic data augmentation strategy to overcome self-supervised training constraints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期数字媒体的发展对精细的人像操纵技术提出了日益增长的需求，尤其是头部交换——将一张图像中的头部无缝集成到另一张图像的身体上。当前方法主要依赖以人脸为中心的裁剪数据，视角有限，严重限制了其在实际场景中的适用性。这些方法难以处理多样的头部表情、不同的发型以及面部区域之外的自然融合。为解决这些局限，我们提出自适应头部合成（AHS），能够有效处理具有多样头部姿态和表情的完整上半身图像。AHS 引入了一种新颖的头部重演合成数据增强策略，以克服自监督训练的限制，在无需配对训练数据的情况下增强对多样面部表情和朝向的泛化能力。大量实验表明，我们的方法在具有挑战性的真实场景中取得了更优的性能，生成视觉上连贯的结果，并在各种头部朝向和发型下保持身份和表情的保真度。值得注意的是，我们的方法在剧烈表情变化时保持面部身份方面表现出卓越的鲁棒性，并在显著的头部姿态变化下忠实保留配饰。
英文原文摘要 1339 字符
Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping--where one image's head is seamlessly integrated onto another's body. Current approaches predominantly rely on face-centered cropped data with limited view angles, significantly restricting their real-world applicability. These methods 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 our approach achieves superior performance in challenging real-world scenarios, producing visually coherent results that preserve both identity and expression fidelity across various head orientations and hairstyles. Notably, our method shows exceptional robustness in maintaining facial identity while drastic expression changes and faithfully preserving accessories while significant head pose variations.