论文标题
ACE-net：通过锚和轮廓估算的高级面对面对齐
ACE-Net: Fine-Level Face Alignment through Anchors and Contours Estimation
论文作者
论文摘要
我们提出了一个新颖的面部锚和轮廓估算框架ACE-NET，以实现精细的面部对齐任务。 ACE网络预测面部锚和轮廓比传统的面部标志更丰富，同时克服了定义的歧义和不一致之处。我们引入了弱监督的损失，使Ace-net能够从现有的面部地标数据集中学习而无需重新注释。取而代之的是，在训练过程中使用合成数据，可以轻松地从中获得GT轮廓，以弥合地标和真实面轮廓之间的密度差距。我们评估了Ace-net相对于Helen数据集的面部对齐精度，该数据集具有194个注释的面部标志，而它仅在300-W数据集中使用68或36个地标培训。我们表明，Ace-net生成的轮廓比直接从68 GT地标内插的轮廓要好，而Ace-net也优于仅在基于GT Landmarks的轮廓的全面监督下训练的模型。
We propose a novel facial Anchors and Contours Estimation framework, ACE-Net, for fine-level face alignment tasks. ACE-Net predicts facial anchors and contours that are richer than traditional facial landmarks while overcoming ambiguities and inconsistencies in their definitions. We introduce a weakly supervised loss enabling ACE-Net to learn from existing facial landmarks datasets without the need for reannotation. Instead, synthetic data, from which GT contours can be easily obtained, is used during training to bridge the density gap between landmarks and true facial contours. We evaluate the face alignment accuracy of ACE-Net with respect to the HELEN dataset which has 194 annotated facial landmarks, while it is trained with only 68 or 36 landmarks from the 300-W dataset. We show that ACE-Net generated contours are better than contours interpolated straight from the 68 GT landmarks and ACE-Net also outperforms models trained only with full supervision from GT landmarks-based contours.
