Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.07209 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918442361159680 |
|---|---|
| author | InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Bao, Hujun Zhai, Hongjia Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Liu, Xianbin Xiang, Xiaojun Zhang, Xiaoyu Chen, Xinyu Wang, Yifu Chen, Yipeng Fan, Zhenzhou Le, Zhewen Ye, Zhichao Zhao, Ziqiang |
| author_facet | InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Bao, Hujun Zhai, Hongjia Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Liu, Xianbin Xiang, Xiaojun Zhang, Xiaoyu Chen, Xinyu Wang, Yifu Chen, Yipeng Fan, Zhenzhou Le, Zhewen Ye, Zhichao Zhao, Ziqiang |
| contents | Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07209 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling InSpatio Team Shen, Donghui Zhang, Guofeng Liu, Haomin Ji, Haoyu Bao, Hujun Zhai, Hongjia Liu, Jialin Guo, Jing Wang, Nan Pan, Siji Pan, Weihong Xie, Weijian Liu, Xianbin Xiang, Xiaojun Zhang, Xiaoyu Chen, Xinyu Wang, Yifu Chen, Yipeng Fan, Zhenzhou Le, Zhewen Ye, Zhichao Zhao, Ziqiang Computer Vision and Pattern Recognition Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos. |
| title | INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.07209 |