arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.15693cs.CV
收藏

Skyra:通过 grounded artifact reasoning 实现 AI 生成视频检测

Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

Department of Automation, Tsinghua University(清华大学自动化系)

Yifei Li, Wenzhao Zheng, Yanran Zhang, Runze Sun, Yu Zheng, Lei Chen, Jie Zhou, Jiwen Lu

AI总结:

本文提出 Skyra,一种专门用于识别 AI 生成视频中人类可感知的视觉瑕疵的多模态大语言模型,通过这些瑕疵作为基础证据进行检测和解释,同时构建了首个大规模 AI 生成视频瑕疵数据集并提出两阶段训练策略。

摘要:

本文提出Skyra,一种专门用于识别AI生成视频中人类可感知的视觉瑕疵的多模态大语言模型,通过这些瑕疵作为基础证据进行检测和解释,同时构建了首个大规模AI生成视频瑕疵数据集并提出两阶段训练策略。

英文摘要:

The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video artifact dataset with fine-grained human annotations. We then develop a two-stage training strategy that systematically enhances our model's spatio-temporal artifact perception, explanation capability, and detection accuracy. To comprehensively evaluate Skyra, we introduce ViF-Bench, a benchmark comprising 3K high-quality samples generated by over ten state-of-the-art video generators. Extensive experiments demonstrate that Skyra surpasses existing methods across multiple benchmarks, while our evaluation yields valuable insights for advancing explainable AI-generated video detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑