发布日期: 2025-07-11

更新日期: 2025-07-12

文章字数: 1k

阅读时长: 4 分

阅读次数:

⚠️ 以下所有内容总结都来自于大语言模型的能力，如有错误，仅供参考，谨慎使用
🔴 请注意：千万不要用于严肃的学术场景，只能用于论文阅读前的初筛！
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ，还请您给我们一些鼓励！⭐️ HuggingFace免费体验

2025-07-11 更新

DArFace: Deformation Aware Robustness for Low Quality Face Recognition

Authors:Sadaf Gulshad, Abdullah Aldahlawi Thakaa

Facial recognition systems have achieved remarkable success by leveraging deep neural networks, advanced loss functions, and large-scale datasets. However, their performance often deteriorates in real-world scenarios involving low-quality facial images. Such degradations, common in surveillance footage or standoff imaging include low resolution, motion blur, and various distortions, resulting in a substantial domain gap from the high-quality data typically used during training. While existing approaches attempt to address robustness by modifying network architectures or modeling global spatial transformations, they frequently overlook local, non-rigid deformations that are inherently present in real-world settings. In this work, we introduce DArFace, a Deformation-Aware robust Face recognition framework that enhances robustness to such degradations without requiring paired high- and low-quality training samples. Our method adversarially integrates both global transformations (e.g., rotation, translation) and local elastic deformations during training to simulate realistic low-quality conditions. Moreover, we introduce a contrastive objective to enforce identity consistency across different deformed views. Extensive evaluations on low-quality benchmarks including TinyFace, IJB-B, and IJB-C demonstrate that DArFace surpasses state-of-the-art methods, with significant gains attributed to the inclusion of local deformation modeling.The code is available at the following https://github.com/sadafgulshad1/DArFace

人脸识别系统通过利用深度神经网络、先进的损失函数和大规模数据集取得了显著的成功。然而，它们在涉及低质量面部图像的现实世界场景中性能往往会下降。这种退化在监控录像或远距离成像中很常见，包括低分辨率、运动模糊和各种失真，与训练期间通常使用的高质量数据之间存在巨大的领域差距。虽然现有方法试图通过修改网络架构或建模全局空间变换来提高稳健性，但它们经常忽略现实环境中固有的局部非刚性变形。在这项工作中，我们介绍了DArFace，一个变形感知的稳健人脸识别框架，它提高了对这种退化的稳健性，而无需配对高质量和低质量的训练样本。我们的方法通过对面部图像进行全局变换（例如旋转、平移）和局部弹性变形来模拟真实的低质量条件。此外，我们引入了一个对比目标来强制不同变形视图之间的身份一致性。在低质量基准测试上的广泛评估，包括TinyFace、IJB-B和IJB-C，证明DArFace超越了最先进的方法，其显著收益归功于局部变形建模的引入。代码可在以下网址找到：DArFace的GitHub地址。

论文及项目相关链接

PDF

Summary

本文介绍了一种名为DArFace的新型面部识别框架，它采用深度神经网络和先进的损失函数来提高对低质量面部图像的识别能力。与传统方法相比，DArFace框架能在低分辨率、运动模糊和多种失真等情况下提高性能。此外，该框架引入了一种新的对比目标函数来强化不同变形视图之间的身份一致性。实验证明，DArFace在低质量面部图像识别方面优于现有技术，其显著优势在于引入了局部变形建模。

Key Takeaways