| title | World2Minecraft: Occupancy-Driven Simulated Scenes Construction |
|---|---|
| authors | Lechao Zhang, Haoran Xu, Jingyu Gong, Xuhong Wang, Yuan Xie, Xin Tan |
| date | 2026-04-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2604.27578 |
| upvotes | 4 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Embodied intelligence requires high-fidelity simulation environments to support 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(VLN). However, we observe that reconstruction quality heavily depends on accurate occupancy prediction, which remains limited by data scarcity and poor generalization in existing models. We introduce a low-cost, automated, and scalable data acquisition pipeline for creating customized occupancy datasets, and demonstrate its effectiveness through MinecraftOcc, a large-scale dataset featuring 100,165 images from 156 richly detailed indoor scenes. Extensive experiments show that our dataset provides a critical complement to existing datasets and poses a significant challenge to current SOTA methods. These findings contribute to improving occupancy prediction and highlight the value of World2Minecraft in providing a customizable and editable platform for personalized embodied AI research. Project page:https://world2minecraft.github.io/. |
cite
@misc{zhang2026world,
title={World2Minecraft: Occupancy-Driven Simulated Scenes Construction},
author={Lechao Zhang and Haoran Xu and Jingyu Gong and Xuhong Wang and Yuan Xie and Xin Tan},
year={2026},
eprint={2604.27578},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2604.27578}
}