Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

AI-Generated Video Detection via Perceptual Straightening

About

The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse. Existing detection methods often struggle with generalization and capturing subtle temporal inconsistencies. We propose ReStraV(Representation Straightening Video), a novel approach to distinguish natural from AI-generated videos. Inspired by the "perceptual straightening" hypothesis -- which suggests real-world video trajectories become more straight in neural representation domain -- we analyze deviations from this expected geometric property. Using a pre-trained self-supervised vision transformer (DINOv2), we quantify the temporal curvature and stepwise distance in the model's representation domain. We aggregate statistics of these measures for each video and train a classifier. Our analysis shows that AI-generated videos exhibit significantly different curvature and distance patterns compared to real videos. A lightweight classifier achieves state-of-the-art detection performance (e.g., 97.17% accuracy and 98.63% AUROC on the VidProM benchmark), substantially outperforming existing image- and video-based methods. ReStraV is computationally efficient, it is offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection.

Christian Intern\`o, Robert Geirhos, Markus Olhofer, Sunny Liu, Barbara Hammer, David Klindt• 2025

Related benchmarks

TaskDatasetResultRank
AI-generated Video DetectionEA-Video seen (evaluation)
Accuracy73.6
88
Synthetic Video DetectionGenVideo (test)
Average Detection Rate92.49
34
Video Forgery DetectionGenVideo (test)
Recall (Average)82
31
AI-generated Video DetectionEvalCrafter
Floor33 Score98.33
28
AI-generated Video DetectionVideoPhy 1.0 (test)
CVX Score78.09
28
AI-generated Video DetectionEA-Video (test)
Accuracy65.4
24
Video Forgery DetectionOOD (Out-of-Domain) Video
Vidu Q164.8
16
Video Forgery DetectionMintVid OOD
Fact Score65
16
Video Forgery DetectionVideo Datasets ID (In-Domain) GenBuster++, LOKI
GenBuster++ Score50.7
16
Video Forgery DetectionID, OOD, and OOD-MintVid Aggregated
Average Score53.2
16
Showing 10 of 33 rows

Other info

Follow for update