AI-Generated Video Detection via Perceptual Straightening

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 for Video), a novel approach to distinguish natural from AI-generated videos. Inspired by the "perceptual straightening" hypothesis [1, 2]-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 [3]), substantially outperforming existing image-and video-based methods. ReStraV is computationally efficient, offering a low-cost and effective detection solution. This work provides new insights into using neural representation geometry for AI-generated video detection. Classifier (e.g., MLP) In representation SSE space, natural videos trace straighter paths than AIgenerated videos. The trajectory geometry provides a discriminative signal. SSE (e.g., DINOv2) Frames are processed by a SSE and we collect the embeddings. Classifier: AI-generated vs. natural Trajectories in representation domain AI-Generated AI-Generated vs. Natural Natural .. .