Improve Model Card: Add Robotics Pipeline, lerobot Library, and Links

README.md

@@ -1,3 +1,42 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: robotics
+library_name: lerobot
+---
+
+# Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions
+
+This repository presents the framework and models from the paper [Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions](https://huggingface.co/papers/2511.04665).
+
+## Abstract
+Robotic manipulation policies are advancing rapidly, but their direct evaluation in the real world remains costly, time-consuming, and difficult to reproduce, particularly for tasks involving deformable objects. Simulation provides a scalable and systematic alternative, yet existing simulators often fail to capture the coupled visual and physical complexity of soft-body interactions. We present a real-to-sim policy evaluation framework that constructs soft-body digital twins from real-world videos and renders robots, objects, and environments with photorealistic fidelity using 3D Gaussian Splatting. We validate our approach on representative deformable manipulation tasks, including plush toy packing, rope routing, and T-block pushing, demonstrating that simulated rollouts correlate strongly with real-world execution performance and reveal key behavioral patterns of learned policies. Our results suggest that combining physics-informed reconstruction with high-quality rendering enables reproducible, scalable, and accurate evaluation of robotic manipulation policies.
+
+## Project Resources
+*   **Project Page:** https://real2sim-eval.github.io/
+*   **GitHub Repository:** https://github.com/kywind/real2sim-eval
+
+## Framework Overview
+The **Real-to-Sim-Policy-Eval** framework facilitates the evaluation of robotic manipulation policies, especially for tasks involving deformable objects. It constructs soft-body digital twins from real-world videos and renders robots, objects, and environments with photorealistic fidelity using 3D Gaussian Splatting.
+
+The main components of this framework include:
+- Constructing simulation assets: visualizing object Gaussians, articulating robot Gaussians, defining and rendering different object layouts.
+- Deploying trained [PhysTwin](https://github.com/Jianghanxiao/PhysTwin) to simulate deformable object Gaussians.
+- Training policies using the `policy_training` submodule, which leverages the `lerobot` library.
+- Evaluating policies in the constructed simulation environment.
+- Interactive control of the Gaussian-based simulation.
+
+<p align="center">
+  <img src="https://github.com/kywind/real2sim-eval/raw/main/assets/media/teaser.jpg" alt="Teaser Image" width="700"/>
+</p>
+
+For detailed installation instructions, running policy evaluation, interactive control, and motion replay, please refer to the [GitHub repository](https://github.com/kywind/real2sim-eval).
+
+## Citation
+```bibtex
+@article{zhang2025real,
+    title={Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions},
+    author={Zhang, Kaifeng and Sha, Shuo and Jiang, Hanxiao and Loper, Matthew and Song, Hyunjong and Cai, Guangyan and Xu, Zhuo and Hu, Xiaochen and Zheng, Changxi and Li, Yunzhu},
+    journal={arXiv preprint arXiv:2511.04665},
+    year={2025}
+}
+```