用扩散模型生成婴儿脸并保持表情一致性，实现高保真匿名化
BLANKET: Anonymizing Faces in Infant Video Recordings
- 先用扩散模型生成与原身份匹配的随机人脸
- 通过时序一致的换脸和表情迁移融入视频帧
- 优于DeepPrivacy2，保留面部特征且无明显伪影
针对婴幼儿视频数据的伦理使用需求，提出BLANKET（基于关键点一致性的婴儿脸保护匿名化）方法，实现对婴儿面部的隐私保护。该方法分两阶段：首先利用扩散模型进行图像修复生成与原身份兼容的随机人脸；其次通过时序一致的面部替换和真实表情迁移，将新面孔无缝嵌入每一帧视频。在短时婴儿视频数据集上评估，对比主流方法DeepPrivacy2，本方法在去标识化程度、面部属性保留、下游任务（如人体姿态估计）影响及伪影控制方面均表现更优。代码已开源，提供简易匿名化演示。
原文摘要 · Abstract (English)
Ensuring the ethical use of video data involving human subjects, particularly infants, requires robust anonymization methods. We propose BLANKET (Baby-face Landmark-preserving ANonymization with Keypoint dEtection consisTency), a novel approach designed to anonymize infant faces in video recordings while preserving essential facial attributes. Our method comprises two stages. First, a new random face, compatible with the original identity, is generated via inpainting using a diffusion model. Second, the new identity is seamlessly incorporated into each video frame through temporally consistent face swapping with authentic expression transfer. The method is evaluated on a dataset of short video recordings of babies and is compared to the popular anonymization method, DeepPrivacy2. Key metrics assessed include the level of de-identification, preservation of facial attributes, impact on human pose estimation (as an example of a downstream task), and presence of artifacts. Both methods alter the identity, and our method outperforms DeepPrivacy2 in all other respects. The code is available as an easy-to-use anonymization demo at https://github.com/ctu-vras/blanket-infant-face-anonym.
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。