论文标题

Vitruvio:3D建筑物通过单角度草图

Vitruvio: 3D Building Meshes via Single Perspective Sketches

论文作者

Tono, Alberto, Huang, Heyaojing, Agrawal, Ashwin, Fischer, Martin

论文摘要

当今的建筑工程和构建(AEC)软件需要学习曲线,以生成三维建筑物的表示。这限制了快速验证通过单个草图传达的初始设计思想的体积含义的能力。允许设计师将单个草图转换为3D建筑物将使所有者能够在不需要认知负载的情况下立即可视化3D项目信息。如果单个视图重建(SVR)的先前最新的(SOTA)数据驱动的方法从单个图像或草图中显示出重建过程中的出色结果,则它们缺乏AEC中的特定应用,分析和实验。因此,这项研究解决了这一差距,引入了仅关注旨在将单个草图转换为3D建筑物网格的建筑物的第一种深度学习方法:Vitruvio。 Vitruvio在特定的建筑数据集(曼哈顿1K)上适应了SVR任务的占用网络。这种适应带来了两个主要的改进。首先,它将推理过程加速超过26%(从0.5s到0.37)。其次,它将重建精度(通过倒角距离衡量)提高了18%。在AEC域中的这种适应过程中,我们评估了建筑物方向在学习过程中的效果,因为它构成了重要的设计因素。在将所有建筑物与规范姿势保持一致的同时,它改善了整体定量指标,但在更复杂的建筑形状中并未捕获细粒细节(如我们的定性分析所示)。最后,Vitruvio从单个角度的草图中输出了带有任意拓扑和属的3D打印建筑网格,提供了前进的一步,以允许所有者和设计师通过2D,有效,直觉和通用的通信媒介传达3D信息:草图。

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.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源