Abstract
Despite rapid progress, world models still lack explicit, persistent structural memory, making it difficult to preserve consistent world structure during continual scene expansion and cross-view revisits. To address this limitation, we present WorldWeave, a world generation framework that decouples world-state maintenance from visual rendering. Specifically, WorldWeave combines continual elevation-map generation with agent-guided scene organization and stitching to build an expandable explicit 3D world that incrementally extends structural memory while preserving existing structure. First, its terrain module uses diffusion-based image outpainting to generate continuous metric elevation maps under neighborhood conditioning and boundary constraints. Next, an agent integrates user intent, terrain evidence, and cross-region connectivity constraints to construct scenes through hierarchical semantic planning, deterministic geometry compilation, and local revision. Finally, during visual generation, planned camera trajectories query world geometry through a read-only interface, producing depth sequences that guide video synthesis without writing the generated results back into the world state. As a result, structural memory remains independent of short-window video generation, enabling continual expansion without predefined map boundaries and providing a consistent geometric basis for observations across trajectories and repeated visits.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Huang, Y., Jiang, L., Hao, Q., Chen, C., Wu, B., Ren, X., He, X., & Zhao, D. (2026). WorldWeave: Growing Persistent Geometric Worlds for Video Generation. https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation
MLA 9
Huang, Yifan, et al. "WorldWeave: Growing Persistent Geometric Worlds for Video Generation." https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation.
Chicago (author–date)
Huang, Yifan, Lifan Jiang, Qingyue Hao, Cheng Chen, Boxi Wu, Xiaoxue Ren, Xiaofei He, and Dehai Zhao. 2026. "WorldWeave: Growing Persistent Geometric Worlds for Video Generation." https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation.
Harvard
Huang, Y., Jiang, L., Hao, Q., Chen, C., Wu, B., Ren, X., He, X. and Zhao, D. (2026) 'WorldWeave: Growing Persistent Geometric Worlds for Video Generation', Available at: https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation.
Vancouver
Huang Y, Jiang L, Hao Q, Chen C, Wu B, Ren X, et al. WorldWeave: Growing Persistent Geometric Worlds for Video Generation. https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation
IEEE
Y. Huang, L. Jiang, Q. Hao, C. Chen, B. Wu, X. Ren, X. He, and D. Zhao, "WorldWeave: Growing Persistent Geometric Worlds for Video Generation," https://omanscience.com/en/articles/worldweave-growing-persistent-geometric-worlds-for-video-generation.