AI RESEARCH
Quantitative Video World Model Evaluation for Geometric-Consistency
arXiv CS.CV
•
ArXi:2605.15185v1 Announce Type: new Generative video models are increasingly studied as implicit world models, yet evaluating whether they produce physically plausible 3D structure and motion remains challenging. Most existing video evaluation pipelines rely heavily on human judgment or learned graders, which can be subjective and weakly diagnostic for geometric failures. We