SyncAI.news, a Varaisys broadcasting
The Rhythm of Generated Video: Latent Chunking Leaves Periodic Traces in Compressed Bitstreams
CY

Chen Ye Gan, Bryan Zhen Zhang, Gene Wen, Yuxing han

· 1 min read

ResearcharXiv cs.CV

The Rhythm of Generated Video: Latent Chunking Leaves Periodic Traces in Compressed Bitstreams

arXiv:2611.22996v1 Announce Type: new Abstract: Most AI-generated video detectors analyze decoded pixels and overlook how videos are produced. We show that causal video autoencoders leave an architecture-specific rhythm in compressed bitstreams: their temporal stride concentrates unpredictable content at latent-chunk boundaries, so rate-distortion optimized encoders allocate bits periodically. Without decoding pixels, we observe four-frame pulses in CogVideoX and Wan2.2 and eight-frame pulses in LTX-Video, which are absent from content-matched camera footage. Passing camera footage through a generator's autoencoder alone induces the pulse, supporting its proposed origin. A training-free peak-ratio statistic separates generated from camera video (AUC 0.84-0.94) and persists across tested quantization settings and H.264/H.265 encoding. Frame-size traces also identify four commercial generators, with 89.2%, 84.1%, and 83.0% accuracy under H.264, H.265, and AV1, beating the pixel-based UnivFD baseline (72.7-73.6%). Our results directly link generative architecture to measurable coding demand.

Original source

This story was published by arXiv cs.CV and written by Chen Ye Gan, Bryan Zhen Zhang, Gene Wen, Yuxing han. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News