Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems

Antonios Tragoudaras, Daniil Cherniavskii, Chenyu Zhang, Antonis Vozikis, Thijmen Nijdam, Derck W. E. Prinzhorn, Mark Bodracska, Nicu Sebe, Andrii Zadaianchuk, Stratis Gavves

Keywords: Vision and Learning; Video Generation; Physics Evaluation

Domains: Vision and Learning, Robotics

TL;DR: Morpheus, a physics-informed evaluation framework for assessing adherence to Newtonian Mechanics in Video Generative Models

Abstract:

Recent advances in image and video generation raise hopes that these models possess world modeling capabilities—the ability to generate realistic, physically plausible videos. This could revolutionize applications in robotics, autonomous driving, and scientific simulation. However, before treating these models as world models, we must ask: Do they adhere to physical laws? Current evaluation methods rely on subjective judgments or trajectory matching, limiting their usage for physical reasoning estimation, where many generations could be physically plausible. Thus, we introduce Morpheus, one of the first physics-informed evaluation frameworks for measuring the ability of video generation models to comprehend Newtonian dynamics. Morpheus features 130 real-world videos capturing physical phenomena, guided by conservation laws. Using those as conditioning for video generation, we assess physical plausibility leveraging interpretable metrics evaluated with respect to infallible conservation laws known per physical setting, leveraging advances in physics-informed neural networks and vision-language foundation models. Importantly, Morpheus targets controlled Newtonian rigid-body settings to enable quantitative checks. Our findings reveal that even with advanced prompting and video conditioning, contemporary models struggle to encode physical principles despite generating aesthetically pleasing videos. All data, leaderboard, and code are open-sourced at: https://physics-from-video.github.io/morpheus-bench/
Accepted at ICML 2026.
Keywords: Vision and Learning; Video Generation, Physical Reasoning.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 114