CVDec 25, 2025

GeCo: A Differentiable Geometric Consistency Metric for Video Generation

arXiv:2512.22274v13 citationsh-index: 19
Originality Incremental advance
AI Analysis

This work addresses the challenge of evaluating and improving geometric consistency in video generation for researchers and practitioners, though it is incremental as it builds on existing metrics and methods.

The authors tackled the problem of detecting geometric deformation and occlusion-inconsistency artifacts in video generation by introducing GeCo, a differentiable geometric consistency metric that produces interpretable consistency maps and was used to benchmark models and reduce artifacts as a guidance loss.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes