Abstract A new automatic layout scheme for interior furniture is presented. According to user-specified furniture, an empty room region is divided into several functional areas by use of conditional generative adversarial networks. Each type of functional area can contain some categories of particular furniture objects, while each category of furniture belongs to one or several types of functional areas. We design a data-driven approach to place the furniture in all the functional areas. We expound the learning process of the division of the functional areas for the case with the user-specified furniture constraint, including to improve the furniture vector, objective function, and training process. Experiments show the proposed layout scheme has advantages in performance and effect compared with existing methods.

中文翻译：

---

带有用户指定家具的自动室内布局

摘要 提出了一种新的室内家具自动布局方案。根据用户指定的家具，使用条件生成对抗网络将一个空房间区域划分为几个功能区域。每一类功能区都可以包含某些类别的特定家具对象，而每一类家具又属于一种或几种类型的功能区。我们设计了一种数据驱动的方法，将家具放置在所有功能区域。针对用户指定家具约束的案例，阐述了功能区划分的学习过程，包括改进家具向量、目标函数和训练过程。实验表明，与现有方法相比，所提出的布局方案在性能和效果上具有优势。