NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911183588556800 |
|---|---|
| author | Zhao, Yanpeng Guan, Shanyan Wang, Yunbo Ge, Yanhao Li, Wei Yang, Xiaokang |
| author_facet | Zhao, Yanpeng Guan, Shanyan Wang, Yunbo Ge, Yanhao Li, Wei Yang, Xiaokang |
| contents | We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the science fiction novel Simulacron-3 (1964), our system constructs expansive environments where only the regions actively explored by the user are rendered with high visual realism through object-centric 3D representations. Unlike previous approaches that rely on global world generation or 2D hallucination, NeoWorld models key foreground objects in full 3D, while synthesizing backgrounds and non-interacted regions in 2D to ensure efficiency. This hybrid scene structure, implemented with cutting-edge representation learning and object-to-3D techniques, enables flexible viewpoint manipulation and physically plausible scene animation, allowing users to control object appearance and dynamics using natural language commands. As users interact with the environment, the virtual world progressively unfolds with increasing 3D detail, delivering a dynamic, immersive, and visually coherent exploration experience. NeoWorld significantly outperforms existing 2D and depth-layered 2.5D methods on the WorldScore benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24441 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding Zhao, Yanpeng Guan, Shanyan Wang, Yunbo Ge, Yanhao Li, Wei Yang, Xiaokang Computer Vision and Pattern Recognition We introduce NeoWorld, a deep learning framework for generating interactive 3D virtual worlds from a single input image. Inspired by the on-demand worldbuilding concept in the science fiction novel Simulacron-3 (1964), our system constructs expansive environments where only the regions actively explored by the user are rendered with high visual realism through object-centric 3D representations. Unlike previous approaches that rely on global world generation or 2D hallucination, NeoWorld models key foreground objects in full 3D, while synthesizing backgrounds and non-interacted regions in 2D to ensure efficiency. This hybrid scene structure, implemented with cutting-edge representation learning and object-to-3D techniques, enables flexible viewpoint manipulation and physically plausible scene animation, allowing users to control object appearance and dynamics using natural language commands. As users interact with the environment, the virtual world progressively unfolds with increasing 3D detail, delivering a dynamic, immersive, and visually coherent exploration experience. NeoWorld significantly outperforms existing 2D and depth-layered 2.5D methods on the WorldScore benchmark. |
| title | NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.24441 |