Research map / Detection and segmentation / CNN features
Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection
Hongyan Fei, Zexi Jia, Chuanwei Huang, Jinchao Zhang, Jie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add specular reflection branch to image branch (ablation) | SRI-Net · DiFF | AUC (%): 66.0 -> 83.9 | Improved |
| add MSR texture and direct light with two-stage cross-attention to Img+SPR (ablation) | SRI-Net · DiFF | AUC (%): 83.9 -> 86.8 | Improved |
| replace BFM mean texture with Retinex-based T_msr (ablation) | SRI-Net · DiFF | AUC (%): 79.9 -> 86.8 | Improved |
| replace BFM PCA-fitted texture with Retinex-based T_msr (ablation) | SRI-Net · DF40 | AUC (%): 88.2 -> 90.9 | Improved |
| add shape normalization (ablation) | SRI-Net · DF40 | AUC (%): 83.7 -> 90.9 | Improved |
| use cross-attention instead of SE-block fusion (ablation) | SRI-Net · DiFF | AUC (%): 84.5 -> 86.8 | Improved |
| use cross-attention instead of concatenation (ablation) | SRI-Net · CelebDF-v2 | AUC (%): 85.6 -> 87.5 | Improved |
| apply Gaussian blurring to test images (ablation) | SRI-Net · DF40 | AUC (%): 90.9 -> 88.7 | Hurt |
| apply JPEG compression to test images (ablation) | SRI-Net · DF40 | AUC (%): 90.9 -> 90.2 | No clear effect |
| apply Gaussian noise to test images (ablation) | SRI-Net · DiFF | AUC (%): 86.8 -> 85.5 | Hurt |
| use MSR texture alone as input (ablation) | SRI-Net · DiFF | AUC (%): 66.0 (Img) vs 60.8 (MSR) | Hurt |
Closest papers by meaning
- From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes (NeurIPS 2025 · similarity 0.89)
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · similarity 0.88)
- FakeDiffer: Distributional Disparity Learning on Differentiated Reconstruction for Face Forgery Detection (AAAI 2025 · similarity 0.88)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.88)
- FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge (NeurIPS 2024 · similarity 0.87)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
