cs.RONov 6, 2026

OfficeTwin: Realizing 3D Reconstruction of Redundant Scenes through Partial Viewpoint Perception

Authors: Quanyun Wu, Kyle Gao, Daisy Li, Kshitij Goyal, Dayou Mao, David A. Clausi, Jonathan Li, Yuhao Chen

Organizations: University of waterloo · University of aalto

Abstract

Feed-forward 3D reconstruction turns an uncalibrated monocular stream into a dense point cloud in a single inference pass, orders of magnitude faster than classical structure-from-motion (e.g., COLMAP), and reliable on the weakly textured, repetitive surfaces where keypoint matching fails outright. However, raw point clouds lack the object identity, physical properties, and watertight volume required for robot learning. This gap widens under robot-native capture. A camera mounted on a robot constrained to a few degrees of freedom sees each object only partially, and the repetitive, weakly textured structure of an office makes distinct workstations nearly indistinguishable, leaving redundant and partial observations that downstream reconstruction cannot resolve. Existing image-to-3D generation methods struggle with these conditions, hallucinating geometry under incomplete views and confusing repeated instances. We present OfficeTwin, a robot-native framework that converts these incomplete observations into simulation-ready digital twins. OfficeTwin first imposes metric and structural constraints, then exploits the office's structural redundancy by registering repeated cubicles into a shared canonical frame, where complementary observations recover geometry occluded in any single view without hallucination. On a real office scan, OfficeTwin recovers every cubicle as an individually watertight, metric solid, outperforming feed-forward reconstruction and generative baselines that fail to produce simulation-ready assets.

Figures & tables

Explore similar work

CardsList
  1. Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations

    Apr 29, 2026Andrii Zadaianchuk, Leonardo Barcellona, Lennard Schuenemann +73D ReconstructionObject Pose Estimation

  2. OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute

    Sep 28, 2026Brandon Leblanc, Charalambos PoullisMulti-View 3D ReconstructionPseudo-Labeling

  3. Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views

    May 8, 2026Grzegorz Wilczynski, Mikołaj Zielinski, Bartosz Świrta +2Multi-View Consistency3D Reconstruction