论文标题
智能主页3D：仅来自语言描述的自动3D-House设计
Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
论文作者
论文摘要
家庭设计是一项复杂的任务，通常要求建筑师完成其专业技能和工具。令人着迷的是，如果一个人可以直观地制定房屋计划而不了解有关家庭设计和使用复杂设计工具的经验，例如通过自然语言。在本文中，我们将其作为一种语言条件的视觉内容生成问题提出，该问题将进一步分为平面图生成和内部纹理（例如地板和墙壁）综合任务。生成过程的唯一控制信号是用户描述房屋详细信息的语言表达。为此，我们提出了一个房屋计划生成模型（HPGM），该模型首先将语言输入转换为结构图表示，然后通过图形条件的布局预测网络（GC LPN）预测房间的布局，并用语言条件纹理GAN（LCT-GAN）生成室内纹理。有了一些后处理，此任务的最终产品是3D房屋型号。为了培训和评估我们的模型，我们构建了第一个文本到3D House模型数据集。
Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intuitively without knowing much knowledge about home design and experience of using complex designing tools, for example, via natural language. In this paper, we formulate it as a language conditioned visual content generation problem that is further divided into a floor plan generation and an interior texture (such as floor and wall) synthesis task. The only control signal of the generation process is the linguistic expression given by users that describe the house details. To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN). With some post-processing, the final product of this task is a 3D house model. To train and evaluate our model, we build the first Text-to-3D House Model dataset.
