Cover Image

Quantitative Video World Model Evaluation for Geometric-Consistency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Jiaxin, Pi, Yihao, Zhang, Yinling, Li, Yuheng, Zou, Xueyan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PanoWorld: Geometry-Consistent Panoramic Video World Modeling
by: Jiang, Le, et al.
Published: (2026)

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
by: Wu, Haoyu, et al.
Published: (2025)

ShareVerse: Multi-Agent Consistent Video Generation for Shared World Modeling
by: Zhu, Jiayi, et al.
Published: (2026)

WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling
by: Fang, Shaoheng, et al.
Published: (2025)

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting
by: Fang, Ye, et al.
Published: (2025)

AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
by: Wang, Zun, et al.
Published: (2026)

MIND: Benchmarking Memory Consistency and Action Control in World Models
by: Ye, Yixuan, et al.
Published: (2026)

Rethinking Video Generation Model for the Embodied World
by: Deng, Yufan, et al.
Published: (2026)

Sekai: A Video Dataset towards World Exploration
by: Li, Zhen, et al.
Published: (2025)

Large-Scale 3D Medical Image Pre-training with Geometric Context Priors
by: Wu, Linshan, et al.
Published: (2024)

Boximator: Generating Rich and Controllable Motions for Video Synthesis
by: Wang, Jiawei, et al.
Published: (2024)

Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment
by: Tang, Jinzhou, et al.
Published: (2025)

Mirage2Matter: A Physically Grounded Gaussian World Model from Video
by: Gao, Zhengqing, et al.
Published: (2026)

Owl-1: Omni World Model for Consistent Long Video Generation
by: Huang, Yuanhui, et al.
Published: (2024)

WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs
by: Yang, Deshun, et al.
Published: (2024)

Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latent Space
by: Zhu, Jian, et al.
Published: (2025)

Video Generation with Consistency Tuning
by: Wang, Chaoyi, et al.
Published: (2024)

Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
by: Liu, Junming, et al.
Published: (2026)

WorldModelBench: Judging Video Generation Models As World Models
by: Li, Dacheng, et al.
Published: (2025)

A Survey: Spatiotemporal Consistency in Video Generation
by: Yin, Zhiyu, et al.
Published: (2025)

Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation
by: Tang, Zhijiang, et al.
Published: (2026)

LoopNav: Benchmarking Spatial Consistency in World Models
by: Lian, Kewei, et al.
Published: (2025)

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
by: Sun, Yujing, et al.
Published: (2025)

UVCG: Leveraging Temporal Consistency for Universal Video Protection
by: Li, KaiZhou, et al.
Published: (2024)

PISCO: Precise Video Instance Insertion with Sparse Control
by: Gao, Xiangbo, et al.
Published: (2026)

Pack and Force Your Memory: Long-form and Consistent Video Generation
by: Wu, Xiaofei, et al.
Published: (2025)

"PhyWorldBench": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models
by: Gu, Jing, et al.
Published: (2025)

GSV3D: Gaussian Splatting-based Geometric Distillation with Stable Video Diffusion for Single-Image 3D Object Generation
by: Tao, Ye, et al.
Published: (2025)

VideoCogQA: A Controllable Benchmark for Evaluating Cognitive Abilities in Video-Language Models
by: Li, Chenglin, et al.
Published: (2024)

Pre-Trained Video Generative Models as World Simulators
by: He, Haoran, et al.
Published: (2025)

Depth-Consistent 3D Gaussian Splatting via Physical Defocus Modeling and Multi-View Geometric Supervision
by: Deng, Yu, et al.
Published: (2025)

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
by: Zhang, Ruohong, et al.
Published: (2024)

Video Depth Anything: Consistent Depth Estimation for Super-Long Videos
by: Chen, Sili, et al.
Published: (2025)

MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos
by: He, Xuehai, et al.
Published: (2024)

Interpreting Physics in Video World Models
by: Joseph, Sonia, et al.
Published: (2026)

Tangram: Benchmark for Evaluating Geometric Element Recognition in Large Multimodal Models
by: Zhang, Chao, et al.
Published: (2024)

MoCA-Video: Motion-Aware Concept Alignment for Consistent Video Editing
by: Zhang, Tong, et al.
Published: (2025)

Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA
by: Song, Zijie, et al.
Published: (2025)

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
by: Zhang, Runze, et al.
Published: (2025)

Pandora: Towards General World Model with Natural Language Actions and Video States
by: Xiang, Jiannan, et al.
Published: (2024)