研究人员开发了一个名为Physics Question Scene Graph (PQSG) 的新评估框架，用于评估AI模型生成的视频在物理上的合理性。PQSG采用基于分层问题的方法，利用视觉语言模型识别生成内容中违反物理定律的地方。该框架使用包含人类标注的FinePhyEval数据集进行了验证，并证明与人类判断的相关性高于以往的方法。研究还发现，PQSG在物理真实性方面将Sora 2和Veo 3等闭源模型排在Wan 2.1之前。 AI
影响 该框架可以通过提供更好的评估指标，促使AI生成的视频在物理上更加真实。
排序理由 该集群描述了一篇介绍AI生成视频新评估框架的新研究论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granular evaluation methods for localizing and specifying physical law violations in …
A vision-language model-based hierarchical question graph framework evaluates video generation models' adherence to physical laws with granular violation detection and human correlation validation.
arXiv:2606.25306v1 Announce Type: new Abstract: Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical laws. Compounding this is a lack of reliable granular evaluation methods for local…