OfficeTwin: Realizing 3D Reconstruction of Redundant Scenes through Partial Viewpoint Perception
Overview
This research introduces OfficeTwin, a robot-native framework that converts incomplete observations from cameras mounted on robots with limited degrees of freedom into simulation-ready digital twins. By imposing metric and structural constraints and registering repeated office cubicles into a shared canonical frame, the system recovers occluded geometry without hallucination. On a real office scan, OfficeTwin successfully reconstructs every cubicle as an individually watertight, metric solid, outperforming feed-forward reconstruction and generative baselines that fail to produce simulation-ready assets under these conditions.
Generated from attributed reports · Updated 13 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
No current evidence-backed claims. Missing information remains not reported.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalOfficeTwin: Realizing 3D Reconstruction of Redundant Scenes through Partial Viewpoint Perception
This research introduces OfficeTwin, a robot-native framework that converts incomplete observations from cameras mounted on robots with limited degrees of freedom into simulation-ready digital twins. By imposing metric and structural constraints and registering repeated office cubicles into a shared canonical frame, the system recovers occluded geometry without hallucination. On a real office scan, OfficeTwin successfully reconstructs every cubicle as an individually watertight, metric solid, outperforming feed-forward reconstruction and generative baselines that fail to produce simulation-ready assets under these conditions.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).