GeoState: Learning View-Decoupled Geometry States for 3D World Modeling
GeoState decouples scene geometry from camera motion for predictive 3D world modeling.
2 stories, newest first · one card per story
GeoState decouples scene geometry from camera motion for predictive 3D world modeling.
Predicted states can be decoded under predicted or specified cameras without per-frame scale alignment.
Today 202 readers · 216 views · 13 reads · all time 108K views