📄 中文摘要
近年来，土木基础设施检查的进展凸显了在数字双胞胎上进行精确三维损伤可视化的必要性，这超越了传统的二维图像损伤识别。与传统的摄影测量三维重建技术相比，现代方法如神经辐射场（NeRF）和高斯点云（GS）在场景表示、渲染质量和处理无特征区域方面表现更为出色。其中，GS因其高效性而脱颖而出，利用离散的各向异性三维高斯来表示辐射场，而不同于NeRF的连续隐式模型。该研究提出了一种基于GS的数字双胞胎方法，旨在有效实现三维损伤可视化。该方法的关键贡献包括...
基于高斯点云的数字双胞胎三维损伤可视化技术
📄 English Summary
Three-dimensional Damage Visualization of Civil Structures via Gaussian Splatting-enabled Digital Twins
Recent advancements in civil infrastructure inspections highlight the necessity for precise three-dimensional (3D) damage visualization on digital twins, surpassing traditional 2D image-based damage identification. Compared to conventional photogrammetric 3D reconstruction techniques, modern approaches such as Neural Radiance Field (NeRF) and Gaussian Splatting (GS) excel in scene representation, rendering quality, and handling featureless regions. Among these, GS stands out for its efficiency, utilizing discrete anisotropic 3D Gaussians to represent radiance fields, in contrast to NeRF's continuous implicit model. This study introduces a GS-enabled digital twin method designed for effective 3D damage visualization. Key contributions of the method include...