arXiv cs.AI· Sicheng Yu, Liu Liu, Xinjie Wang, Xinjiang Wang, Taojun Ding, Wenhao Hu, Beizhen Zhao, Puxin Yan, Zhizhong Su, Hao Wang·· 10 小时前AI 评分38
GSExplorer:基于持久 3DGS 世界状态的交互式世界生成
GSExplorer: Interactive World Generation with a Persistent 3DGS World State
AI 导读
GSExplorer 是一个以持久 3D Gaussian 世界状态为核心的生成—重建框架,通过 SLAM 重建后端与共享支持掩码实现选择性场景更新和跨块位姿优化。
正文 · 原文
Abstract:Interactive world generation requires both accurate local control and stable scene consistency over long rollouts. Existing methods improve local generation through camera or geometry conditioning and extend historical context with memory mechanisms. However, long-horizon exploration remains challenging due to incomplete target-view guidance and inconsistencies accumulated during scene updates. We present \textbf{GSExplorer}, a generation--reconstruction framework built around a persistent 3D Gaussian world state. At each step, the current 3DGS scene provides multimodal rendering conditions for a video generator, while camera geometry is injected through a separate Relative Ray Encoding branch. Generated videos are then fed back to a SLAM-based reconstruction backend, where appearance and geometric consistency checks produce a shared support mask for selective scene updates and cross-chunk pose refinement. We further design a data-construction pipeline that reproduces realistic 3DGS degradation during scene extrapolation, yielding 293K training pairs of degraded multimodal renderings and real target videos. GSExplorer achieves the best overall performance among the compared methods on both single-step and three-step WorldScore evaluation, including a Camera Control score of 99.07 in single-step extrapolation. On 481-frame leave-and-return rollouts, it also shows strong revisit consistency.
| Comments: | 15 pages |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.01543 [cs.CV] |
| (or arXiv:2611.01543v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.01543 arXiv-issued DOI via DataCite |
Submission history
From: Sicheng Yu [view email]
[v1]
Sun, 1 Nov 2026 04:14:50 UTC (30,833 KB)
[v2]
Wed, 18 Nov 2026 06:38:01 UTC (31,041 KB)
来源:arXiv cs.AI · arxiv.org