Ahmed Doghri Logo Image
Ahmed Doghri

d3video

Synthetic video can match frame-to-frame motion and still wobble one derivative deeper. d3video reads that second-order trace and separates every generated clip.

d3video reproduced benchmark result

Fake Motion Hides In The Next Derivative

Generated video can keep average velocity plausible while alternating tiny temporal corrections from frame to frame. First-order motion sees the speed. It misses the wobble.

d3video creates matched real and synthetic trajectories. Both share smooth global motion; generated clips receive a small alternating correction designed to preserve the obvious statistics.

Difference Of Differences

The detector computes frame displacement, then differences those displacements again. A single threshold on mean second-order magnitude performs the classification.

No model, training split, or feature extractor is needed. That makes the detector cheap and the evidence legible, while compression robustness remains a separate question.

The Number

The first-order baseline scores 46% (below chance) on 200 held-out trajectories. Second-order discrepancy reaches 100% on the same set, a 54-point gain.

This is a controlled forensic benchmark, not a guarantee on arbitrary internet video. The repository links the four-dataset research result separately from its own number.

Research Basis

Inspired by ICCV 2025's D3 video detector. The portfolio number above comes from this repository's own controlled benchmark, not from the paper.

Tools Used

Python
Video Forensics
Temporal Features
Deepfake Detection
Signal Processing
unittest
GitHub Actions CI