Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908599535534080 |
|---|---|
| author | Zhu, Xiaoming Huang, Xu Xie, Qinghongbing Deng, Zhi Yu, Junsheng Guan, Yirui Liu, Zhongyuan Zhu, Lin Zhao, Qijun Liu, Ligang Zeng, Long |
| author_facet | Zhu, Xiaoming Huang, Xu Xie, Qinghongbing Deng, Zhi Yu, Junsheng Guan, Yirui Liu, Zhongyuan Zhu, Lin Zhao, Qijun Liu, Ligang Zeng, Long |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15564 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation Zhu, Xiaoming Huang, Xu Xie, Qinghongbing Deng, Zhi Yu, Junsheng Guan, Yirui Liu, Zhongyuan Zhu, Lin Zhao, Qijun Liu, Ligang Zeng, Long Computer Vision and Pattern Recognition 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. |
| title | Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.15564 |