# DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments

arXiv: https://arxiv.org/abs/2507.21981 · HTML: https://mlsanity.com/paper/2507.21981/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2025.

## Built on by (most cited first, 12 of 12)

- [Towards Physically Executable 3D Gaussian for Embodied Navigation](https://mlsanity.com/paper/2510.21307/) (2025)
- [EvoVLA: Self-Evolving Vision-Language-Action Model](https://mlsanity.com/paper/2511.16166/) (2025)
- [TwinAligner: Visual-Dynamic Alignment Empowers Physics-aware Real2Sim2Real for Robotic Manipulation](https://mlsanity.com/paper/2512.19390/) (2025)
- [ManiVID-3D: Generalizable View-Invariant Reinforcement Learning for Robotic Manipulation via Disentangled 3D Representations](https://mlsanity.com/paper/2509.11125/) (2025)
- [AOMGen: Photoreal, Physics-Consistent Demonstration Generation for Articulated Object Manipulation](https://mlsanity.com/paper/2512.18396/) (2025)
- [IGen: Scalable Data Generation for Robot Learning from Open-World Images](https://mlsanity.com/paper/2512.01773/) (2025)
- [Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform](https://mlsanity.com/paper/2512.08478/) (2025)
- [From Seeing to Simulating: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and Evaluation](https://mlsanity.com/paper/2604.15805/) (2026)
- [REAP: Reinforcement-Learning End-to-End Autonomous Parking with Gaussian Splatting Simulator for Real2Sim2Real Transfer](https://mlsanity.com/paper/2605.08713/) (2026)
- [Mirage2Matter: A Physically Grounded Gaussian World Model from Video](https://mlsanity.com/paper/2602.00096/) (2026)
- [AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight](https://mlsanity.com/paper/2607.14997/) (2026)
- [φ-RIE: From Photorealistic Reconstruction to Interactive Environments](https://mlsanity.com/paper/2609.26795/) (2026)

## Abstract (arXiv)

We present the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridging the Sim2Real gap. Powered by Gaussian Splatting and MuJoCo, Discoverse enables massively parallel simulation of multiple sensor modalities and accurate physics, with inclusive supports for existing 3D assets, robot models, and ROS plugins, empowering large-scale robot learning and complex robotic benchmarks. Through extensive experiments on imitation learning, Discoverse demonstrates state-of-the-art zero-shot Sim2Real transfer performance compared to existing simulators. For code and demos: https://air-discoverse.github.io/.