SPLIT: Training-Free AI-Generated and Partially Edited Video Detection via Spatial Patch-Level Incoherence and Temporal Roughness
About
Deploying AI-generated video detectors in real-world services demands an ultra-low false positive rate (FPR) on real videos to avoid falsely rejecting authentic content, a regime where standard metrics such as AUROC fail to reflect actual operating behavior. We introduce Spatial Patch-Level Incoherence and Temporal Roughness (SPLIT), a training-free detector that operates on patch tokens from a frozen vision encoder to detect both fully generated and partially edited videos. SPLIT computes two complementary signals: Two-step Temporal Roughness (TTR), capturing non-smooth patch trajectories via one-step and two-step feature variation contrast, and Local Spatial Motion Incoherence (LSMI), measuring spatially inconsistent temporal changes through gradients of a feature-space motion field. The two are fused multiplicatively with gamma correction to sharpen real-fake separation at strict thresholds. We further propose a service-aligned evaluation protocol based on Fake Recall at fixed FPR with real-only threshold calibration and cross-real threshold transfer. Across three benchmarks (FakeParts, GenVideo, and ViF-Bench), SPLIT achieves the highest Fake Recall at FPR = $0.1\%$, substantially outperforming supervised and training-free baselines while remaining robust to post-processing with negligible overhead. The code is publicly available at https://github.com/mldljyh/SPLIT .
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| AI-generated Video Detection | GenVideo | HotShot Score100 | 43 | |
| Fake Video Detection | ViF-Bench | CogX1.593.56 | 24 | |
| AI-Generated and Edited Video Detection | FakeParts | Extrapolation Fake Recall @ 0.1% FPR97.86 | 12 | |
| Fake Video Detection | ViF-Bench cross-real threshold transfer FPR=1% | Overall Fake Recall95.08 | 12 | |
| Video Deepfake Detection | ViF-Bench cross-real threshold transfer | CogX1.5 Score84.77 | 12 |