Learning Representations for Masked Facial Recovery
Learning Representations for Masked Facial Recovery
复制标题
DOI：
10.1007/978-3-031-20713-6_2
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Zaigham A. Randhawa;Shivang Patel;D. Adjeroh;Gianfranco Doretto
中科院分区：
文献类型：
--
作者：
Zaigham A. Randhawa;Shivang Patel;D. Adjeroh;Gianfranco Doretto
最近几年的大流行导致在公共场所佩戴防护口罩的人急剧增加。这对人脸识别技术的普遍使用构成了明显的挑战，目前人脸识别技术的性能正在下降。解决这个问题的一种方法是恢复到Face恢复方法作为预处理步骤。目前的人脸重建和操作方法利用了对人脸流形进行建模的能力，但往往是通用的。我们介绍了一种特定的方法，用于从同一人戴面具的图像中恢复人脸图像。为此，我们设计了一种专门的GaN反转方法，基于一组适当的损耗来学习无掩蔽编码器。通过大量的实验，我们证明了该方法在人脸图像去掩蔽方面的有效性。此外，我们还在几个人脸识别基准数据集上证明了身份信息被很好地保存，从而提高了人脸验证的性能。
The pandemic of these very recent years has led to a dramatic increase in people wearing protective masks in public venues. This poses obvious challenges to the pervasive use of face recognition technology that now is suffering a decline in performance. One way to address the problem is to revert to face recovery methods as a preprocessing step. Current approaches to face reconstruction and manipulation leverage the ability to model the face manifold, but tend to be generic. We introduce a method that is specific for the recovery of the face image from an image of the same individual wearing a mask. We do so by designing a specialized GAN inversion method, based on an appropriate set of losses for learning an unmasking encoder. With extensive experiments, we show that the approach is effective at unmasking face images. In addition, we also show that the identity information is preserved sufficiently well to improve face verification performance based on several face recognition benchmark datasets.