RoboOccWorld predicts future 3D occupancy for indoor robots by conditioning an autoregressive transformer on the next camera pose, outperforming OccWorld on a restructured ScanNet benchmark.
Embodiedscan: A holistic multi-modal 3d perception suite towards embodied ai
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Occupancy World Model for Robots
RoboOccWorld predicts future 3D occupancy for indoor robots by conditioning an autoregressive transformer on the next camera pose, outperforming OccWorld on a restructured ScanNet benchmark.