发表机构
Arizona State University; Prelight Inc（亚利桑那州立大学; 普雷莱特公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究对6种文本引导模型开展首次大规模人脸编辑评估，构建含169个属性的Face-Edit-Attributes数据集，发现多数模型头发配饰编辑表现好但姿态编辑差，存在过度编辑及针对深色皮肤男性和老年面孔的偏差。
AI 中文摘要
人脸外观编辑为FaceApp和Photoshop等热门应用提供支持。生成对抗网络（GANs）和3D可变形模型（3DMMs）已被广泛用于人脸编辑。GANs可执行多样的人脸编辑（例如更改发色、发型），但常产生不稳定的编辑效果；3DMMs可产生稳定的编辑效果，但只能更改姿态和面部表情。近来，Nano Banana等文本引导的扩散模型在图像编辑中变得流行，它们是GANs和3DMMs的有力替代方案，因为既能产生稳定又多样的图像编辑效果。尽管文本引导模型已被广泛测试用于全场景编辑（例如“让这位女性弹吉他”），但尚未在人脸编辑任务中得到全面测试。我们针对序列人脸编辑任务，对6种流行的文本引导模型开展了首次大规模评估（共评估约100万张图像）。我们推出了Face-Edit-Attributes，这是聚焦于头发、配饰和姿态编辑的最大型人脸编辑属性集合，包含169个属性。我们使用两个流行的名人脸数据集CelebA和CelebSET来比较模型性能。结果显示，多数模型在头发和配饰编辑上表现良好，但在姿态编辑上存在困难；所有模型均存在过度编辑问题（例如仅要求更改发型时却更改了发色）。我们还评估了各模型的人口统计学偏差，结果显示过度编辑存在令人惊讶的偏差：几乎所有模型对深色皮肤男性面孔和老年面孔产生了更多的过度编辑。我们的结果代码和数据（包括约100万张图像的存储库）可在此处访问。
英文摘要
Facial appearance editing powers popular applications like FaceApp and Photoshop. Generative Adversarial Networks (GANs) and 3D Morphable Models (3DMMs) have been widely used for facial editing. GANs can perform varied facial edits (e.g., changing hair color, hairstyle), but often produce unstable edits. 3DMMs produce stable edits, but can only alter pose and facial expression. Recently, text-guided diffusion models like Nano Banana have become popular for image editing. Text-guided models are a compelling alternative to GANs and 3DMMs since they can produce both stable and varied image edits. While text-guided models have been widely tested for whole-scene edits (e.g., ``make the woman play a guitar''), they have not been comprehensively tested for facial editing. We conducted the first large-scale evaluation ($\sim1$M images evaluated) of six popular text-guided models on a sequential facial editing task. We present Face-Edit-Attributes, the largest collection of $169$ facial editing attributes focused on hair, accessories, and pose edits. We compared model performance using two popular celebrity face datasets: CelebA and CelebSET. Our results show that most models performed hair and accessory edits well, but struggled with editing pose. All models over-edit (e.g., changing hair color when asked only to change the hairstyle). We also evaluated demographic biases in each model. Our results show surprising biases in overediting: almost all models created more overedits for dark-skinned male faces and old faces. The code and data for our results (including our repository of $\sim 1$M images) can be accessed \href{https://github.com/rahul1801/Face-Edit-Bench}{\textcolor{blue}{here}}.
CommentsACM Multimedia (ACMMM) 2026 Oral
