AUEditNet：基于隐式解耦的双分支面部动作单元强度操控
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
AI总结：
针对多AU强度标注数据稀缺问题，本文提出双分支AUEditNet，仅用18名受试者即可隐式解耦身份与属性，实现12个AU的精确强度操控。
摘要：
面部动作单元（AU）强度在量化细粒度表情行为方面发挥着关键作用，是面部表情操控的有效条件。然而，包含多个AU强度标注的公开数据集仍然严重有限，并且通常受试者数量较少。这一限制因解耦问题给图像中的AU强度操控带来挑战，导致研究人员借助其他大型数据集以及预训练AU强度估计器来生成伪标签。为解决这一约束并充分利用AU强度的人工标注以实现精确操控，我们提出了AUEditNet。所提出的模型实现了跨12个AU的出色强度操控，并且仅使用18名受试者即可有效训练。通过采用双分支架构，我们的方法实现了面部属性与身份的全面解耦，无需额外损失函数，也无需使用大批量训练。该方法为在数据集受试者数量有限的情况下实现理想的面部属性编辑提供了一种潜在解决方案。实验表明，AUEditNet在编辑AU强度方面具有更高的准确性，证实了其在有限受试者群体内解耦面部属性和身份的能力。AUEditNet支持以强度值或目标图像作为条件，无需为特定面部表情合成构建AU组合。此外，AU强度估计作为下游任务验证了真实图像与编辑图像之间的一致性，确认了我们所提出的AU强度操控方法的有效性。
英文摘要：
Facial action unit (AU) intensity plays a pivotal role in quantifying fine-grained expression behaviors, which is an effective condition for facial expression manipulation. However, publicly available datasets containing intensity annotations for multiple AUs remain severely limited, often featuring a restricted number of subjects. This limitation places challenges to the AU intensity manipulation in images due to disentanglement issues, leading researchers to resort to other large datasets with pretrained AU intensity estimators for pseudo labels. In addressing this constraint and fully leveraging manual annotations of AU intensities for precise manipulation, we introduce AUEditNet. Our proposed model achieves impressive intensity manipulation across 12 AUs, trained effectively with only 18 subjects. Utilizing a dual-branch architecture, our approach achieves comprehensive disentanglement of facial attributes and identity without necessitating additional loss functions or implementing with large batch sizes. This approach offers a potential solution to achieve desired facial attribute editing despite the dataset's limited subject count. Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool. AUEditNet allows conditioning by either intensity values or target images, eliminating the need for constructing AU combinations for specific facial expression synthesis. Moreover, AU intensity estimation, as a downstream task, validates the consistency between real and edited images, confirming the effectiveness of our proposed AU intensity manipulation method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
