Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918242930393088 |
|---|---|
| author | Xiao, Zeqi Zhao, Yiwei Li, Lingxiao Lan, Yushi Yu, Ning Garg, Rahul Cooper, Roshni Taghavi, Mohammad H. Pan, Xingang |
| author_facet | Xiao, Zeqi Zhao, Yiwei Li, Lingxiao Lan, Yushi Yu, Ning Garg, Rahul Cooper, Roshni Taghavi, Mohammad H. Pan, Xingang |
| contents | We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video4Spatial, a framework showing that video diffusion models conditioned solely on video-based scene context can perform complex spatial tasks. We validate on two tasks: scene navigation - following camera-pose instructions while remaining consistent with 3D geometry of the scene, and object grounding - which requires semantic localization, instruction following, and planning. Both tasks use video-only inputs, without auxiliary modalities such as depth or poses. With simple yet effective design choices in the framework and data curation, Video4Spatial demonstrates strong spatial understanding from video context: it plans navigation and grounds target objects end-to-end, follows camera-pose instructions while maintaining spatial consistency, and generalizes to long contexts and out-of-domain environments. Taken together, these results advance video generative models toward general visuospatial reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03040 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation Xiao, Zeqi Zhao, Yiwei Li, Lingxiao Lan, Yushi Yu, Ning Garg, Rahul Cooper, Roshni Taghavi, Mohammad H. Pan, Xingang Computer Vision and Pattern Recognition Artificial Intelligence We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video4Spatial, a framework showing that video diffusion models conditioned solely on video-based scene context can perform complex spatial tasks. We validate on two tasks: scene navigation - following camera-pose instructions while remaining consistent with 3D geometry of the scene, and object grounding - which requires semantic localization, instruction following, and planning. Both tasks use video-only inputs, without auxiliary modalities such as depth or poses. With simple yet effective design choices in the framework and data curation, Video4Spatial demonstrates strong spatial understanding from video context: it plans navigation and grounds target objects end-to-end, follows camera-pose instructions while maintaining spatial consistency, and generalizes to long contexts and out-of-domain environments. Taken together, these results advance video generative models toward general visuospatial reasoning. |
| title | Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.03040 |