Real-to-Sim-to-Real technique is gaining increasing interest for robotic manipulation, as it can generate scalable data in simulation while having narrower sim-to-real gap. However, previous methods mainly focused on environment-level visual real-to-sim transfer, ignoring the transfer of interactions, which could be challenging and inefficient to obtain purely in simulation especially for contact-rich tasks. We propose ExoGS, a robot-free 4D Real-to-Sim-to-Real framework that captures both static environments and dynamic interactions in the real world and transfers them seamlessly to a simulated environment. It provides a new solution for scalable manipulation data collection and policy learning. ExoGS employs a self-designed robot-isomorphic passive exoskeleton AirExo-3 to capture kinematically consistent trajectories with millimeter-level accuracy and synchronized RGB observations during direct human demonstrations. The robot, objects, and environment are reconstructed as editable 3D Gaussian Splatting assets, enabling geometry-consistent replay and large-scale data augmentation. Additionally, a lightweight Mask Adapter injects instance-level semantics into the policy to enhance robustness under visual domain shifts. Real-world experiments demonstrate that ExoGS significantly improves data efficiency and policy generalization compared to teleoperation-based baselines. Code and hardware files have been released on https://github.com/zaixiabalala/ExoGS.
@article{arxiv.2601.18629,
title = {ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection},
author = {Yiming Wang and Ruogu Zhang and Minyang Li and Hao Shi and Junbo Wang and Deyi Li and Jieji Ren and Wenhai Liu and Weiming Wang and Hao-Shu Fang},
journal= {arXiv preprint arXiv:2601.18629},
year = {2026}
}