AI RESEARCH
Measuring 3D Spatial Geometric Consistency in Dynamic Generated Videos
arXiv CS.CV
•
ArXi:2603.19048v1 Announce Type: new Recent generative models can produce high-fidelity videos, yet they often exhibit 3D spatial geometric inconsistencies. Existing evaluation methods fail to accurately characterize these inconsistencies: fidelity-centric metrics like FVD are insensitive to geometric distortions, while consistency-focused benchmarks often penalize valid foreground dynamics. To address this gap, we