Morpheus: Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments
This addresses the need for reliable physical reasoning in video generative models for applications like robotics and autonomous driving, representing an incremental step in benchmarking.
The paper tackles the problem of assessing whether video generation models adhere to physical conservation laws by introducing Morpheus, a benchmark with 80 real-world videos and physics-informed metrics, finding that current models struggle to encode physical principles despite generating aesthetically pleasing videos.
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 conservation laws? To answer this, we introduce Morpheus, a benchmark for evaluating video generation models on physical reasoning. It features 80 real-world videos capturing physical phenomena, guided by conservation laws. Since artificial generations lack ground truth, we assess physical plausibility using physics-informed metrics evaluated with respect to infallible conservation laws known per physical setting, leveraging advances in physics-informed neural networks and vision-language foundation models. Our findings reveal that even with advanced prompting and video conditioning, current models struggle to encode physical principles despite generating aesthetically pleasing videos. All data, leaderboard, and code are open-sourced at our project page.