Research map / Image generation / Autoregressive and latent generation
FaceForensics++: Learning to Detect Manipulated Facial Images
Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Niessner
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 |
|---|---|---|---|
| crop the tracked face region instead of feeding the full image (ablation) | XceptionNet · FaceForensics++ test, HQ | accuracy (%): 74.78 -> 95.73 | Improved |
| crop the tracked face region instead of feeding the full image (ablation) | XceptionNet · FaceForensics++ test, Raw | accuracy (%): 82.01 -> 99.26 | Improved |
| crop the tracked face region instead of feeding the full image (ablation) | XceptionNet · FaceForensics++ test, LQ | accuracy (%): 70.52 -> 81.00 | Improved |
| increase training corpus from 10 to 300 videos (ablation) | XceptionNet · FaceForensics++ test, Compressed 40, all methods | accuracy (%): 60.55 -> 76.01 | Improved |
| increase training corpus from 10 to 300 videos (ablation) | XceptionNet · FaceForensics++ test, Compressed 23, all methods | accuracy (%): 67.71 -> 92.65 | Improved |
| increase training corpus from 10 to 300 videos (ablation) | XceptionNet · FaceForensics++ test, Raw, all methods | accuracy (%): 92.81 -> 98.88 | Improved |
| use video compression (raw to LQ) on the test data | Steg. Features + SVM · FaceForensics++ test | accuracy (%): 97.63 -> 55.98 | Hurt |
| use video compression (raw to LQ) on the test data | XceptionNet · FaceForensics++ test | accuracy (%): 99.26 -> 81.00 | Hurt |
| use ImageNet-pretrained deep XceptionNet instead of shallow CNNs | XceptionNet vs MesoNet · FaceForensics++ test, LQ | accuracy (%): 70.47 -> 81.00 | Improved |
| test on NeuralTextures instead of DeepFakes | XceptionNet · FaceForensics++ manipulation-specific, Compressed 40 | accuracy (%): 94.28 -> 82.11 | Hurt |
| lower video quality for human observers (raw to LQ) | Human observers · user study | accuracy (%): 68.69 -> 58.73 | Hurt |
| use automatic detector instead of human observers | XceptionNet · FaceForensics++ LQ | accuracy (%): 58.73 -> 81.00 | Improved |
Closest papers by meaning
- DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection (CVPR 2020 · similarity 0.93)
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces (NeurIPS 2025 · similarity 0.89)
- DF40: Toward Next-Generation Deepfake Detection (NeurIPS 2024 · similarity 0.89)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.89)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.89)
- A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning (NeurIPS 2024 · similarity 0.88)
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.
