vae-rhythm / README.md
multimodalart's picture
multimodalart HF Staff
Upload README.md with huggingface_hub
4bc4c77 verified
|
Raw History Blame Contribute Delete
3.13 kB
metadata
title: VAE Rhythm
emoji: 🎼
colorFrom: yellow
colorTo: indigo
sdk: gradio
sdk_version: 6.32.0
app_file: app.py
python_version: '3.12'
startup_duration_timeout: 1h
short_description: Detect AI-generated video via VAE decoding traces

VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection

Demo for the paper VAE Rhythm: Temporal Decoding Traces for AI-Generated Video Detection (arXiv 2611.21114, Show Lab Β· NUS). It ships the paper's two detectors:

  1. Phase scan (training-free) β€” re-encode a clip with the paper's protocol (x264 CRF 23, GOP 32, short side capped at 720 px), reconstruct K=24 successive W=13-frame windows with a frozen causal Wan2.1 video VAE, and read the periodicity of the reconstruction-error residual. Generated videos are decoded in frame groups, so their error profile repeats with the group period; real videos give a nearly flat one.
  2. CaDet (trained detector, Jack97/CaDet) β€” two parameter-efficient paths on a frozen DINOv3 ViT-L/16 read 8 frames per clip and output a sum of z-scores standardised on real validation videos.

Interpretation

  • Phase scan: a high z(Ppk) (above β‰ˆ 2.35, the 95th percentile of real videos) is evidence that a clip was decoded by a causal video VAE. A low value is not evidence that a video is real β€” low motion, frame-rate conversion, upscaling and re-encoding all weaken the rhythm.
  • CaDet: the score is a z-score sum (β‰ˆ 0 for typical real videos, larger = more likely generated), not a probability. Operating points shift across real-video sources; heavily re-encoded, very short or low-resolution clips are harder.
  • Neither score alone is a definitive real/fake verdict.

Examples

Each example is a VAE pair built with the paper's own recipe: a stock clip from the CC0 dataset linoyts/repo-to-space-example-videos, protocol-encoded, next to a copy of the same frames through one Wan2.1 VAE round trip re-encoded with the same chain. The pairs showcase the contrast a VAE round trip leaves in the traces. Measured on this Space: the cat pair scans Ppk 0.477 vs 0.091 (C8 0.82 vs 0.11) and the rope pair 0.311 vs 0.135 (low motion β€” see the warning in the app), while the 50 fps veggie pair's scan contrast is weak (frame-rate conversion weakens the rhythm, as the interpretation rules note). The CaDet score rises for the round-trip twin in all three pairs (βˆ’0.84β†’βˆ’0.20, 2.62β†’3.10, 3.30β†’5.69). Clip names are neutral on purpose β€” no ground-truth authenticity claim is made about the stock footage itself.

References