GeCo: A Differentiable Geometric Consistency Metric for Video Generation

Leslie Gu, Junhwa Hur, Charles Herrmann, Fangneng Zhan, Todd Zickler +2 more
12/25/2025
cs.CV

No official code found. Best implementation: ShixuanGu/GeCo (11 stars, last commit 2026-04-30).

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.

View on arXivView PDF

Code Implementations(1)

ShixuanGu/GeCoCommunity68%

GeCo: A Differentiable Geometric Consistency Metric for Video Generation

110PythonDec 16, 20255 months ago

Similar Papers

Cite this paper

@article{gu2025geco,
  title  = {GeCo: A Differentiable Geometric Consistency Metric for Video Generation},
  author = {Leslie Gu and Junhwa Hur and Charles Herrmann and Fangneng Zhan and Todd Zickler and Deqing Sun and Hanspeter Pfister},
  year   = {2025},
  eprint = {2512.22274},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.22274v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.22274.svg)](https://codeofpaper.com/paper/2512.22274)

Discussion