Search papers, labs, and topics across Lattice.
FunRec reconstructs functional 3D scene representations from egocentric RGB-D videos by jointly estimating articulated parts, their kinematic parameters, and 3D motion. It operates on in-the-wild human interaction sequences without requiring controlled setups or CAD priors, enabling the recovery of interactable 3D scenes. Experiments on real and simulated data show FunRec significantly outperforms existing methods in part segmentation (+50 mIoU), articulation error (5-10x lower), and reconstruction accuracy.
Unlock interactive digital twins from messy, real-world videos: FunRec automatically turns egocentric RGB-D recordings into simulation-ready 3D scenes.
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.
ETH
Microsoft Research
Stanford HAI