Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos

Authors: Chengguo Zhang, Ping Ping

arXiv: 2609.22267 [cs.CV]

Submitted: 8 September 2026

Accepted: ACM Multimedia 2026 (Oral)

Subjects: Computer Vision and Pattern Recognition (cs.CV); Multimedia (cs.MM)

Abstract

Camera motion often reflects directorial intent and requires professional equipment, making it a high-value form of intellectual property. However, generative video models can imitate such high-value camera motions with simple prompts, while existing similarity detection methods mainly operate on visual content and fail to capture deeper motion similarity. This is primarily because their training data entangles camera motion with visual content. Moreover, traditional optical flow is insufficient to represent complex camera motions.

To address this gap, we build the first benchmark for camera motion analysis, including a motion dataset with 11 motion styles and evaluation protocols. Furthermore, we propose a motion representation that augments optical flow with vorticity cues from fluid dynamics, thereby better capturing motions. Experiments show that our detector achieves a 3.02× improvement in plagiarism detection over the strongest baseline and remains effective on generative videos. We believe our work extends copyright protection beyond static content to dynamic camera motion.

Key Contributions

• First benchmark for camera motion analysis, comprising a motion dataset with 11 motion styles and accompanying evaluation protocols.
• A novel motion representation that augments optical flow with vorticity cues drawn from fluid dynamics, enabling more faithful capture of complex camera movements.
• State-of-the-art detection performance, delivering a 3.02× improvement in plagiarism detection over the strongest baseline while remaining effective on generative videos.

Why It Matters in 2026

As generative video models mature through 2026, the ability to reproduce signature cinematic camera moves—dolly zooms, crane shots, whip pans—from a one-line prompt has turned directorial craft into a new front in the intellectual property debate. Existing similarity detectors, trained on content-entangled data, remain blind to pure motion. By decoupling camera motion from visual content and introducing physics-inspired representations, this work lays the groundwork for protecting dynamic cinematographic authorship in the generative era.

Citation

@inproceedings{zhang2026cameramotion,
  title={Did You Steal My Shot? Pioneering Camera Motion Plagiarism Detection in Generative Videos},
  author={Zhang, Chengguo and Ping, Ping},
  booktitle={Proceedings of the ACM Multimedia 2026},
  year={2026}
}

DOI: https://doi.org/10.48550/arXiv.2609.22267

Full text: arXiv:2609.22267v1

via ArXiv CV