arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.23699cs.CV
收藏

CRONOS:视频模型中反事实物理一致性的基准测试

CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models

University of Freiburg(弗莱堡大学);Max Planck Institute for Informatics(马克斯·普朗克信息研究所);CISPA Helmholtz Center for Information Security(哈勒斯海姆信息安全中心)

León Begiristain, Olaf Dünkel, Adam Kortylewski

AI总结:

提出CRONOS基准,通过干预视角、场景、物体类别和外观四个因素,评估视频模型在固定物理事件类型下反事实物理一致性的表现,发现现有模型存在显著失败。

摘要:

视频预测日益被视为通向通用世界模型的途径,但目前尚不清楚这些系统是学习了潜在的因果结构,还是仅仅利用表面的视觉相关性进行未来预测。我们引入了CRONOS,一个基于干预的基准,旨在评估反事实物理一致性:即模型对物理事件的预测是否对视觉输入中的受控变化(如场景上下文、视角、物体外观和物体类别的变化)做出适当响应。CRONOS构建在逼真的Unreal Engine环境中,能够跨不同场景和动态生成受控、高保真的视频。与之前的基准相比,CRONOS系统性地干预了四个关键因素——视角、场景、物体类别和物体外观——同时保持底层物理事件类型(如碰撞、遮挡或坠落)不变。我们对近期开源视频生成器的评估揭示了反事实物理一致性的显著失败:同一物理事件类型的预测质量受到外观、环境,尤其是视角变化的影响。CRONOS提供了一个受控且可重复的测试平台,用于诊断不同干预下生成视频质量的变化,为开发在多种条件变化下表现一致的模型确立了具体目标。数据集和代码可在我们的项目页面获取。

英文摘要:

Video prediction is increasingly viewed as a path toward generalizable world models, yet it remains unclear whether these systems learn underlying causal structure or merely exploit superficial visual correlations for future prediction. We introduce CRONOS, an intervention-based benchmark to evaluate counterfactual physical consistency: whether a model's predictions of physical events respond appropriately to controlled changes in the visual input, such as variations of camera viewpoint, scene, object category, and object appearance. Built in a photorealistic Unreal Engine environment, CRONOS enables controlled, high-fidelity generation of videos across diverse scenes and dynamics, including sampling multiple physically plausible outcomes of the same physical event. In contrast to previous benchmarks, that evaluate video prediction on scenes CRONOS systematically intervenes on four factors -camera viewpoint, scene, object category, and object appearance- while keeping the underlying physical event type, such as a fall, collision, or occlusion, fixed. Our evaluation of recent open-source video generators reveals substantial failures in counterfactual physical consistency: prediction quality for the same physical event type is affected by appearance, environment, and particularly viewpoint changes. CRONOS provides a controlled and reproducible testbed for diagnosing how generated video quality changes across interventions, establishing a concrete target for developing models that perform consistently across changes of multiple conditions. The dataset and evaluation code are available at our project page.

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。

↑