cs.CVNov 17, 2026

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

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

Organizations: Tsinghua University · University of California, San Diego · New York University Shanghai

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.

Figures & tables

Explore similar work

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

    Nov 16, 2026Ke Sun, Shuwei Li, Haiyang Mei +1Deepfake Detection

  2. Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compressed Bitstream

    Jul 21, 2026Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan KurbanDeepfake DetectionSequential Hypothesis Testing

  3. Mind the Rift: Cross-Scale Coupling Mismatch for AI-Generated Video Detection

    Sep 1, 2026Siyu Li, Jin Yang, Weiheng LiangDigital Image ForensicsDeepfake Detection