Abstract Digital building representations enable and promote new forms of simulation, automation, and information sharing. However, creating and maintaining these representations is prohibitively expensive. In an effort to make the adoption of this technology easier, researchers have been automating the digital modeling of existing buildings by applying reality capture devices and computer vision algorithms. This article is a summary of the efforts of the past ten years, with a particular focus on object recognition methods. We rectify three limitations of existing review articles by describing the general structure and variations of object recognition systems and performing an extensive and quantitative comparative performance evaluation. The coverage of building component classes (i.e. semantic coverage) and recognition performances are reported in-depth and framed using a building taxonomy. Research programs demonstrate sparse semantic coverage with a clear bias towards recognizing floor, wall, ceiling, door, and window classes. Comprehensive semantic coverage of building infrastructure will require a radical scaling and diversification of efforts.

中文翻译：

---

现有建筑的自动化数字建模：视觉对象识别方法综述

摘要 数字建筑表示启用并促进了模拟、自动化和信息共享的新形式。然而，创建和维护这些表示的成本高得令人望而却步。为了更容易地采用这项技术，研究人员一直在通过应用现实捕捉设备和计算机视觉算法来自动化现有建筑物的数字建模。这篇文章是对过去十年努力的总结，特别关注对象识别方法。我们通过描述对象识别系统的一般结构和变化并进行广泛和定量的比较性能评估来纠正现有评论文章的三个局限性。构建组件类的覆盖范围（即 语义覆盖）和识别性能被深入报告并使用建筑分类法进行框架化。研究计划表明语义覆盖稀疏，明显偏向于识别地板、墙壁、天花板、门和窗类。建筑基础设施的全面语义覆盖将需要彻底扩展和多样化工作。