World2Minecraft: Occupancy-Driven Simulated Scenes Construction

ArXi:2604.27578v1 Announce Type: new Embodied intelligence requires high-fidelity simulation environments to perception and decision-making, yet existing platforms often suffer from data contamination and limited flexibility. To mitigate this, we propose World2Minecraft to convert real-world scenes into structured Minecraft environments based on 3D semantic occupancy prediction. In the reconstructed scenes, we can effortlessly perform downstream tasks such as Vision-Language Navigation