高斯建筑网格（GBM）：利用Google Earth和高斯点散布提取建筑的3D网格
Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting
AI总结：
本文提出一种基于Google Earth和高斯点散布的方法，通过建筑名称、地址或地理坐标提取建筑的3D网格。
摘要：
最近发布的开源预训练基础图像分割和目标检测模型（SAM2+GroundingDINO）允许在多视角2D图像中对感兴趣对象进行几何一致的分割。用户可以使用基于文本或点击的提示来分割感兴趣对象，而无需标注训练数据集。高斯点散布允许基于2D图像学习场景的3D表示和辐射。结合Google Earth Studio、SAM2+GroundingDINO、2D高斯点散布以及我们基于形态学操作和轮廓简化的掩码优化改进，我们创建了一个管道，可以根据建筑名称、地址或地理坐标提取任意建筑的3D网格。
英文摘要：
Recently released open-source pre-trained foundational image segmentation and object detection models (SAM2+GroundingDINO) allow for geometrically consistent segmentation of objects of interest in multi-view 2D images. Users can use text-based or click-based prompts to segment objects of interest without requiring labeled training datasets. Gaussian Splatting allows for the learning of the 3D representation of a scene's geometry and radiance based on 2D images. Combining Google Earth Studio, SAM2+GroundingDINO, 2D Gaussian Splatting, and our improvements in mask refinement based on morphological operations and contour simplification, we created a pipeline to extract the 3D mesh of any building based on its name, address, or geographic coordinates.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
