SGF-CDNet: A Consistency-Discrepancy Graph Network over Semantic-Geometric Fused Nodes for Face Forgery Detection
For face forgery detection, this work introduces a novel graph-based approach that jointly models consistency and discrepancy, but the improvement is incremental over existing methods.
SGF-CDNet proposes a graph network that fuses semantic and geometric features to detect subtle disharmony in forged faces, achieving superior performance on public datasets.
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.