We present FunRec, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulated reconstruction, which rely on controlled setups, multi-state captures, or CAD priors, FunRec operates directly on in-the-wild human interaction sequences to recover interactable 3D scenes. It automatically discovers articulated parts, estimates their kinematic parameters, tracks their 3D motion, and reconstructs static and moving geometry in canonical space, yielding simulation-compatible meshes. Across new real and simulated benchmarks, FunRec surpasses prior work by a large margin, achieving up to +50 mIoU improvement in part segmentation, 5-10 times lower articulation and pose errors, and significantly higher reconstruction accuracy. We further demonstrate applications on URDF/USD export for simulation, hand-guided affordance mapping and robot-scene interaction.
Cite
@article{arxiv.2604.05621,
title = {FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos},
author = {Alexandros Delitzas and Chenyangguang Zhang and Alexey Gavryushin and Tommaso Di Mario and Boyang Sun and Rishabh Dabral and Leonidas Guibas and Christian Theobalt and Marc Pollefeys and Francis Engelmann and Daniel Barath},
journal= {arXiv preprint arXiv:2604.05621},
year = {2026}
}