SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry
文献类型：期刊论文
| 作者 | Gao, Lin1,4; Sun, Jia-Mu1,4; Mo, Kaichun3; Lai, Yu-Kun2; Guibas, Leonidas J.; Yang, Jie1,4 |
| 刊名 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
 |
| 出版日期 | 2023-07-01 |
| 卷号 | 45期号:7页码:8902-8919 |
| ISSN号 | 0162-8828 |
| 关键词 | 3Dindoor scene synthesis deep generative model fine-grained mesh generation graph neural network recursive neural network relationship graphs variational autoencoder |
| DOI | 10.1109/TPAMI.2023.3237577 |
| 英文摘要 | 3D indoor scenes are widely used in computer graphics, with applications ranging from interior design to gaming to virtual and augmented reality. They also contain rich information, including room layout, as well as furniture type, geometry, and placement. High-quality 3D indoor scenes are highly demanded while it requires expertise and is time-consuming to design high-quality 3D indoor scenes manually. Existing research only addresses partial problems: some works learn to generate room layout, and other works focus on generating detailed structure and geometry of individual furniture objects. However, these partial steps are related and should be addressed together for optimal synthesis. We propose SCENEHGN, a hierarchical graph network for 3D indoor scenes that takes into account the full hierarchy from the room level to the object level, then finally to the object part level. Therefore for the first time, our method is able to directly generate plausible 3D room content, including furniture objects with fine-grained geometry, and their layout. To address the challenge, we introduce functional regions as intermediate proxies between the room and object levels to make learning more manageable. To ensure plausibility, our graph-based representation incorporates both vertical edges connecting child nodes with parent nodes from different levels, and horizontal edges encoding relationships between nodes at the same level. Our generation network is a conditional recursive neural network (RvNN) based variational autoencoder (VAE) that learns to generate detailed content with fine-grained geometry for a room, given the room boundary as the condition. Extensive experiments demonstrate that ourmethod produces superior generation results, even when comparing results of partial steps with alternative methods that can only achieve these. We also demonstrate that our method is effective for various applications such as part-level room editing, room interpolation, and room generation by arbitrary room boundaries. |
| 资助项目 | ARL[W911NF-21-2-0104] ; Vannevar Bush Faculty Fellowship ; Beijing Municipal Natural Science Foundation[JQ21013] ; National Natural Science Foundation of China[6261136007] ; Open Research Projects of Zhejiang Lab[2021KE0AB06] ; Youth Innovation Promotion Association CAS |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| 出版者 | IEEE COMPUTER SOC |
| WOS记录号 | WOS:001004665900064 |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/21261]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Gao, Lin |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF10 3AT, Wales 3.Stanford Univ, Stanford, CA 94305 USA 4.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Gao, Lin,Sun, Jia-Mu,Mo, Kaichun,et al. SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(7):8902-8919. |
| APA | Gao, Lin,Sun, Jia-Mu,Mo, Kaichun,Lai, Yu-Kun,Guibas, Leonidas J.,&Yang, Jie.(2023).SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(7),8902-8919. |
| MLA | Gao, Lin,et al."SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.7(2023):8902-8919. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。