用文字或坐标一键生成建筑3D网格，无需训练数据。
Gaussian Building Mesh (GBM): Extract a Building's 3D Mesh with Google Earth and Gaussian Splatting
- 结合谷歌地球与分割模型，通过文本或点击定位目标建筑
- 基于2D图像用高斯点云重建建筑三维几何与光影特征
- 自动优化掩码形状，适合快速获取城市建筑3D模型
最近发布的开源预训练图像分割与目标检测模型（SAM2+GroundingDINO）可在多视角2D图像中实现几何一致的物体分割，用户可通过文本或点击提示定位感兴趣对象，无需标注数据集。高斯点云（Gaussian Splatting）可基于2D图像学习场景的三维几何与辐射场表示。结合Google Earth Studio、SAM2+GroundingDINO、2D高斯点云及我们提出的基于形态学操作和轮廓简化的掩码优化方法，构建了一条端到端的流水线，仅需建筑名称、地址或地理坐标即可提取任意建筑的3D网格模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。