Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions

TL;DR

This paper introduces a novel real-to-sim evaluation framework that creates photorealistic soft-body digital twins from real videos, enabling accurate, scalable, and reproducible assessment of robotic manipulation policies involving deformable objects.

Contribution

It presents a new method combining physics-informed reconstruction with Gaussian Splatting rendering to simulate soft-body interactions from real-world data.

Findings

Simulated rollouts strongly correlate with real-world performance.

The framework accurately captures key behavioral patterns of policies.

Enables scalable and reproducible evaluation of deformable object manipulation.

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. Website: https://real2sim-eval.github.io/