外观
论文arXiv 2610.2234313 天前
GeoState：学习视图解耦的几何状态用于3D世界建模
原文链接：GeoState: Learning View-Decoupled Geometry States for 3D World Modeling（arXiv 2610.22343 · 发布日期：2026-10-15）
GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
GeoState将多视角GFM特征聚合为视图解耦场景状态，用于预测3D世界建模，并在Waymo、KITTI和nuScenes验证。
核心要点
- 现有3D世界模型使用GFM特征作状态，但视图依赖会混合场景动态与相机变化。
- 场景tokenizer聚合多视角GFM特征，几何解码器再用相机射线查询观测。
- 自回归世界模型预测未来场景状态，相机运动单独建模，可按预测或指定相机解码。
- 实验显示在Waymo优于既有3D世界模型，支持跨视图查询，并零样本泛化到KITTI和nuScenes。
验证范围与局限：验证包括Waymo实验，以及对KITTI和nuScenes的零样本泛化。
英文摘要 (Abstract)
Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynamics with camera-induced variation, making the resulting state evolution harder to predict. We propose GeoState, a view-decoupled geometry representation for predictive 3D world modeling that separates scene-state evolution from camera-dependent observation. Specifically, a scene tokenizer aggregates multi-view GFM features into a view-decoupled scene state, which a geometry decoder queries using camera rays. An autoregressive world model then predicts future scene states, while camera motion is modeled separately. The predicted states can therefore be decoded under either predicted or externally specified cameras, while retaining a single context-derived scale throughout the rollout without per-frame scale alignment. Experiments show that GeoState outperforms prior 3D world models on Waymo, supports geometrically consistent cross-view querying, and generalizes zero-shot to KITTI and nuScenes. Project page: https://hongchang-liu.github.io/GeoState-project-page/
作者：Hongchang Liu, Jian Liu, Yujuan Ding, Liang Peng, Xun Jiang, Fei Ma, Xing Xu, Yi Bin
来源
本页事实对应的公开页面，以原文为准。