Today's architectural engineering and construction (AEC) software require a learning curve to generate a three-dimension building representation. This limits the ability to quickly validate the volumetric implications of an initial design idea communicated via a single sketch. Allowing designers to translate a single sketch to a 3D building will enable owners to instantly visualize 3D project information without the cognitive load required. If previous state-of-the-art (SOTA) data-driven methods for single view reconstruction (SVR) showed outstanding results in the reconstruction process from a single image or sketch, they lacked specific applications, analysis, and experiments in the AEC. Therefore, this research addresses this gap, introducing the first deep learning method focused only on buildings that aim to convert a single sketch to a 3D building mesh: Vitruvio. Vitruvio adapts Occupancy Network for SVR tasks on a specific building dataset (Manhattan 1K). This adaptation brings two main improvements. First, it accelerates the inference process by more than 26% (from 0.5s to 0.37s). Second, it increases the reconstruction accuracy (measured by the Chamfer Distance) by 18%. During this adaptation in the AEC domain, we evaluate the effect of the building orientation in the learning procedure since it constitutes an important design factor. While aligning all the buildings to a canonical pose improved the overall quantitative metrics, it did not capture fine-grain details in more complex building shapes (as shown in our qualitative analysis). Finally, Vitruvio outputs a 3D-printable building mesh with arbitrary topology and genus from a single perspective sketch, providing a step forward to allow owners and designers to communicate 3D information via a 2D, effective, intuitive, and universal communication medium: the sketch.
翻译:今天的建筑工程和施工 (AEC) 软件需要学习曲线来生成三维建筑表示。这限制了快速验证通过单个草图传达的初始设计想法的体积影响的能力。允许设计师将单个草图转换为 3D 建筑将使所有者可以即时可视化 3D 项目信息,而无需承受认知负荷所需的时间。如果先前的状态-of-the-art (SOTA) 数据驱动的单视图重建 (SVR) 方法在从单个图像或草图的重建过程中展示了杰出的结果,则它们缺乏在 AEC 中的特定应用、分析和实验。因此,本研究填补了这一差距,引入了第一个专注于建筑物的深度学习方法,旨在将单个草图转换为 3D 建筑网格:Vitruvio。 Vitruvio 将 Occupancy Network 适应于特定建筑数据集 (曼哈顿 1K) 上的 SVR 任务。此适应带来两个主要改进。首先,它将推理过程加速了超过 26% (从 0.5 秒到 0.37 秒)。其次,它将重建精度 (通过 Chamfer 距离测量) 增加了 18%。在 AEC 领域的这种适应中,我们评估了建筑定向对学习过程的影响,因为它构成了一个重要的设计因素。虽然将所有建筑物与基准姿势对齐改善了整体定量指标,但没有捕捉到复杂建筑形状的细粒度细节 (如我们的定性分析所示)。最后,Vitruvio 从单个透视草图输出一个可任意拓扑和属于的 3D 可打印建筑网格,为所有者和设计师提供了向 2D、有效、直观和通用的沟通媒介:草图前进了一步。