cs.CV · 2512.22274 Copy arXiv ID · Dec 25, 2025 Save GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure Authors: Leslie Gu , Junhwa Hur , Charles Herrmann , Fangneng Zhan , Todd Zickler , Deqing Sun , Hanspeter Pfister
Organizations: 1Harvard University · 2Google DeepMind · 3MIT
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.
Explore similar work May 18, 2026 · Jan Ackermann, Shengqu Cai, Boyang Deng +3 Optical Flow
Mar 19, 2026 · Weijia Dou, Wenzhao Zheng, Weiliang Chen +3 3D Geometry High-Fidelity Video Generation
Jun 12, 2026 · Xunzhi Xiang, Zixuan Duan, Yabo Chen +8 Pre-Trained Video Diffusion Models
May 18, 2026 · cs.CV J/K move · Enter open · S save
Jan Ackermann, Shengqu Cai, Boyang Deng, Zhengfei Kuang +2
Stanford University · Google DeepMind
Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under camera motion. Existing solutions either improve consistency as a byproduct, apply only to static scenes or realign the latent space of the model completely. We introduce a geometry-consistency reward that directly measures whether motion in a generated video is compatible with a coherent scene. Our key insight is that in physically consistent videos, background motion should be explainable by rigid camera-induced flow, while independently moving objects should preserve appearance identity along motion trajectories. We operationalize this using optical flow, depth--pose predictions, and feature-based correspondence to separate rigid and dynamic regions and evaluate their respective consistency. Integrating this reward with reinforcement fine-tuning transforms geometric consistency from an emergent property into an explicit optimization objective for video generators. The approach is model agnostic and applies to diverse dynamic scenes containing both camera and object motion. Experiments show substantial reductions in temporal geometric artifacts over strong baselines while preserving perceptual quality. Code and model weights are published.