Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Zhengcen, Jiang, Chenyang, Zhao, Hang, Zhou, Shiyang, Mo, Yunyang, Gao, Feng, Yang, Fan, Shan, Qiben, Wu, Shaocong, Su, Jingyong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910105757286400
author Li, Zhengcen
Jiang, Chenyang
Zhao, Hang
Zhou, Shiyang
Mo, Yunyang
Gao, Feng
Yang, Fan
Shan, Qiben
Wu, Shaocong
Su, Jingyong
author_facet Li, Zhengcen
Jiang, Chenyang
Zhao, Hang
Zhou, Shiyang
Mo, Yunyang
Gao, Feng
Yang, Fan
Shan, Qiben
Wu, Shaocong
Su, Jingyong
contents The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detection framework built on the Qwen2.5-VL Vision Transformer, which operates natively at variable spatial resolutions and temporal durations. This native-scale approach effectively preserves the high-frequency artifacts and spatiotemporal inconsistencies typically lost during conventional preprocessing. Extensive experiments demonstrate that our method achieves superior performance across multiple benchmarks, underscoring the critical importance of native-scale processing and establishing a robust new baseline for AI-generated video detection.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04634
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
Li, Zhengcen
Jiang, Chenyang
Zhao, Hang
Zhou, Shiyang
Mo, Yunyang
Gao, Feng
Yang, Fan
Shan, Qiben
Wu, Shaocong
Su, Jingyong
Computer Vision and Pattern Recognition
Artificial Intelligence
The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detection framework built on the Qwen2.5-VL Vision Transformer, which operates natively at variable spatial resolutions and temporal durations. This native-scale approach effectively preserves the high-frequency artifacts and spatiotemporal inconsistencies typically lost during conventional preprocessing. Extensive experiments demonstrate that our method achieves superior performance across multiple benchmarks, underscoring the critical importance of native-scale processing and establishing a robust new baseline for AI-generated video detection.
title Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.04634