多视角分析提升真实人脸伪造检测准确率
Unmasking Facial DeepFakes: A Robust Multiview Detection Framework for Natural Images
- 分三路编码器分别捕捉全局边界、中层纹理与局部表情区域特征
- 在多个数据集上优于传统单视角方法，尤其在姿态变化下表现更稳
- 适合需要高鲁棒性的反深度伪造系统开发者使用
近年来，深度伪造技术发展迅速，可生成高度逼真的合成人脸图像。现有检测方法在姿态变化、遮挡及隐蔽伪影等真实场景下表现不佳。为此，我们提出一种多视角架构，通过多层次分析面部特征增强检测能力。模型集成三个专用编码器：全局视图编码器检测边界不一致，中层视图编码器分析纹理与色彩对齐，局部视图编码器捕捉眼、鼻、口等易出错区域的失真。此外，引入一个姿态编码器，用于分类人脸朝向，确保在不同视角下的检测鲁棒性。通过融合各编码器特征，模型在复杂姿态与光照条件下仍能有效识别伪造图像。实验表明，该方法在多个挑战性数据集上显著优于传统单视角方法。
原文摘要 · Abstract (English)
DeepFake technology has advanced significantly in recent years, enabling the creation of highly realistic synthetic face images. Existing DeepFake detection methods often struggle with pose variations, occlusions, and artifacts that are difficult to detect in real-world conditions. To address these challenges, we propose a multi-view architecture that enhances DeepFake detection by analyzing facial features at multiple levels. Our approach integrates three specialized encoders, a global view encoder for detecting boundary inconsistencies, a middle view encoder for analyzing texture and color alignment, and a local view encoder for capturing distortions in expressive facial regions such as the eyes, nose, and mouth, where DeepFake artifacts frequently occur. Additionally, we incorporate a face orientation encoder, trained to classify face poses, ensuring robust detection across various viewing angles. By fusing features from these encoders, our model achieves superior performance in detecting manipulated images, even under challenging pose and lighting conditions.Experimental results on challenging datasets demonstrate the effectiveness of our method, outperforming conventional single-view approaches
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。