通过融合语义与几何信息，检测人脸伪造中的不协调关系。
SGF-CDNet: A Consistency-Discrepancy Graph Network over Semantic-Geometric Fused Nodes for Face Forgery Detection
- 将人脸解析与关键点信息融合生成节点，捕捉高层语义与精确几何特征。
- 双路径图网络分别评估面部组件的一致性与差异性，识别伪造引入的矛盾。
- 在多个公开数据集上表现领先，适合高精度人脸伪造检测场景。
深度伪造技术的快速发展对鲁棒的人脸伪造检测提出了更高要求。尽管伪造人脸可能无明显伪影，但其不同面部区域间常存在细微不协调。我们提出SGF-CDNet，一种基于语义-几何融合节点的连续性-差异性图网络（CD-GNN）。首先，通过深度融合人脸分割的语义区域与面部关键点的几何信息，构建语义-几何融合节点（SGF nodes），使节点同时具备高层语义理解与精确几何约束能力。其次，设计双路径CD-GNN，在一致性与差异性两个维度并行推理：一致性路径评估面部组件是否符合自然生物规律，差异性路径挖掘伪造引入的结构张力与特征冲突。通过融合两种推理机制，模型能有效识别面部组件间的不协调关系。大量实验表明，SGF-CDNet在多个公开数据集上均取得优异性能，展现出可靠的人脸伪造检测能力。
原文摘要 · Abstract (English)
The rapid advancement of deepfakes necessitates robust face forgery detection. Although forged faces may lack obvious artifacts, they often contain subtle disharmony among different facial regions. We propose SGF-CDNet, a Consistency-Discrepancy Graph Network (CD-GNN) over Semantic-Geometric Fused (SGF) nodes. First, SGF-CDNet constructs SGF nodes by deeply fusing semantic regions from face parsing with geometric information from facial landmarks, allowing nodes to capture both high-level concepts and precise geometric constraints. Next, a dual-path CD-GNN performs parallel relational reasoning on these nodes across two dimensions: consistency and discrepancy. The consistency path evaluates if facial components follow natural biological patterns, while the discrepancy path mines for structural tensions and feature conflicts introduced by forgeries. By integrating these processes, our model effectively identifies disharmonious relationships between facial components. Extensive experiments on public datasets demonstrate that SGF-CDNet achieves superior performance, establishing it as a reliable solution for face forgery detection.
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。