GeoState: Learning View-Decoupled Geometry States for 3D World Modeling

Hongchang Liu, Jian Liu, Yujuan Ding, Liang Peng, Xun Jiang, Fei Ma, Xing Xu, Yi Bin · N/A · 2026

Summary

Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors.

Abstract Summary

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/

Key Points

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.

Method

Our goal is to predict future scene geometry without requiring the world model to simultaneously account for variations induced by camera motion. To this end, as illustrated in Figure 1 , we first construct a view-decoupled geometry state from multi-view observations, and then model its temporal evolution while handling camera evolution separately. GeoState learning.

Experiments

We pretrain the Scene Tokenizer and ray-conditioned decoder on approximately 10k multi-view scenes from DL3DV ( Ling et al., 2024 ) , TartanAir ( Wang et al., 2020 ) , RealEstate10K ( Zhou et al., 2018 ) , CO3D ( Reizenstein et al., 2021 ) , and WildRGB-D ( Xia et al., 2024 ) , using ground-truth depth where available and VGGT-$\Omega$ ( Wang et al., 2026 ) pseudo-depth otherwise.

We then adapt both modules on a subset of the Waymo Open Dataset ( Sun et al., 2020 ) selected for static scene content.

Experiments — GeoState: Learning View-Decoupled Geometry States for 3D World Modeling — Figure 2: Qualitative multi-view depth forecasting. Red boxes highlight prediction differences.

Sources and Demonstrations

Figures are reproduced from Liu et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.