Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality standards, however, necessitates the precise replication of real-world object diversity. Existing datasets demonstrate that this process heavily relies on artist-driven designs, which demand substantial human effort and present significant scalability challenges. To scalably produce realistic and interactive 3D scenes, we first present MetaScenes, a large-scale, simulatable 3D scene dataset constructed from real-world scans, which includes 15366 objects spanning 831 fine-grained categories. Then, we introduce Scan2Sim, a robust multi-modal alignment model, which enables the automated, high-quality replacement of assets, thereby eliminating the reliance on artist-driven designs for scaling 3D scenes. We further propose two benchmarks to evaluate MetaScenes: a detailed scene synthesis task focused on small item layouts for robotic manipulation and a domain transfer task in vision-and-language navigation (VLN) to validate cross-domain transfer. Results confirm MetaScene's potential to enhance EAI by supporting more generalizable agent learning and sim-to-real applications, introducing new possibilities for EAI research. Project website: https://meta-scenes.github.io/.
@article{arxiv.2505.02388,
title = {MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans},
author = {Huangyue Yu and Baoxiong Jia and Yixin Chen and Yandan Yang and Puhao Li and Rongpeng Su and Jiaxin Li and Qing Li and Wei Liang and Song-Chun Zhu and Tengyu Liu and Siyuan Huang},
journal= {arXiv preprint arXiv:2505.02388},
year = {2025}
}