Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
复制标题
DOI：
10.1111/cgf.14357
复制
发表时间：
2021-08
影响因子：
2.5
通讯作者：
Kai Wang;Xianghao Xu-;Leon Lei;Selena Ling;Natalie Lindsay;Angel X. Chang;M. Savva;Daniel Ritchie
中科院分区：
文献类型：
--
作者：
Kai Wang;Xianghao Xu-;Leon Lei;Selena Ling;Natalie Lindsay;Angel X. Chang;M. Savva;Daniel Ritchie
现实的3D室内场景数据集在计算机视觉，场景理解，自主导航和3D重建方面取得了重大进展。幸运的是，Combinatorics在我们的身边：现有的3D场景数据集中有足够的单独房间，如果有一种将它们重组为新布局的方法。 3D房间。一个使用可用的2D楼平面图指导3D房间的选择和变形；另一个人学会了一组兼容的3D房间，并将它们组合成新颖的布局。三个子任务表明，不同的方法在这些子任务上进行了交易，我们调查了从生成的3D场景和讨论策略中受益的下游任务，以选择最适合这些任务需求的方法。
Realistic 3D indoor scene datasets have enabled significant recent progress in computer vision, scene understanding, autonomous navigation, and 3D reconstruction. But the scale, diversity, and customizability of existing datasets is limited, and it is time‐consuming and expensive to scan and annotate more. Fortunately, combinatorics is on our side: there are enough individual rooms in existing 3D scene datasets, if there was but a way to recombine them into new layouts. In this paper, we propose the task of generating novel 3D floor plans from existing 3D rooms. We identify three sub‐tasks of this problem: generation of 2D layout, retrieval of compatible 3D rooms, and deformation of 3D rooms to fit the layout. We then discuss different strategies for solving the problem, and design two representative pipelines: one uses available 2D floor plans to guide selection and deformation of 3D rooms; the other learns to retrieve a set of compatible 3D rooms and combine them into novel layouts. We design a set of metrics that evaluate the generated results with respect to each of the three subtasks and show that different methods trade off performance on these subtasks. Finally, we survey downstream tasks that benefit from generated 3D scenes and discuss strategies in selecting the methods most appropriate for the demands of these tasks.