GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure
arXiv:2512.22274
summary
GeCo is a geometry-based metric that detects deformation and occlusion inconsistencies in generated videos by combining residual motion and depth cues, providing dense consistency maps for benchmarking and guiding video generation models.
Abstract
We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts. We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free guidance loss to reduce deformation artifacts during video generation.
Topics & keywords
#video generation#geometric consistency#motion analysis#depth estimation#occlusion detectionGeCoresidual motiondepth priorsconsistency mapsdeformation artifactstraining-free guidance loss