Generating artistic and coherent 3D scene layouts is crucial in digital content creation. Traditional optimization-based methods are often constrained by cumbersome manual rules, while deep generative models face challenges in producing content with richness and diversity. Furthermore, approaches that utilize large language models frequently lack robustness and fail to accurately capture complex spatial relationships. To address these challenges, this paper presents a novel vision-guided 3D layout generation system. We first construct a high-quality asset library containing 2,037 scene assets and 147 3D scene layouts. Subsequently, we employ an image generation model to expand prompt representations into images, fine-tuning it to align with our asset library. We then develop a robust image parsing module to recover the 3D layout of scenes based on visual semantics and geometric information. Finally, we optimize the scene layout using scene graphs and overall visual semantics to ensure logical coherence and alignment with the images. Extensive user testing demonstrates that our algorithm significantly outperforms existing methods in terms of layout richness and quality. The code and dataset will be available at https://github.com/HiHiAllen/Imaginarium.
@article{arxiv.2510.15564,
title = {Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation},
author = {Xiaoming Zhu and Xu Huang and Qinghongbing Xie and Zhi Deng and Junsheng Yu and Yirui Guan and Zhongyuan Liu and Lin Zhu and Qijun Zhao and Ligang Liu and Long Zeng},
journal= {arXiv preprint arXiv:2510.15564},
year = {2025}
}