MGFs：基于多视角图像的建筑物网格构建的掩码高斯场
MGFs: Masked Gaussian Fields for Meshing Building based on Multi-View Images
AI总结：
本文提出掩码高斯场（MGFs）框架，通过多级掩码与边界损失训练高斯场，在无人机图像上高效且精确地重建建筑物表面网格，并附带提升新视角合成效果。
摘要：
在过去的几十年里，基于图像的建筑物表面重建引起了广泛的研究兴趣，并已在遗产保护、建筑规划等多个领域得到应用。与传统的摄影测量和基于NeRF的解决方案相比，近年来基于高斯场的方法因其训练时间高效且能保留详细的三维信息，在生成表面网格方面展现出显著潜力。然而，大多数基于高斯场的方法使用所有图像像素进行训练，包含建筑物和非建筑物区域，这导致建筑物网格存在显著噪声，并且时间效率下降。本文提出了一种新颖的框架，称为掩码高斯场（Masked Gaussian Fields，MGFs），旨在以时间高效的方式为建筑物生成精确的表面重建。该框架首先应用EfficientSAM和COLMAP生成建筑物的多级掩码以及相应的掩码点云。随后，通过整合两种创新损失来训练掩码高斯场：一种专注于构建建筑物区域的多级感知掩码损失，以及一种旨在增强不同掩码之间边界细节的边界损失。最后，我们改进了基于掩码高斯球体的四面体表面网格提取方法。在无人机图像上的综合实验表明，与传统方法以及几种基于NeRF和基于高斯的SOTA解决方案相比，我们的方法显著提高了建筑物表面重建的准确性和效率。值得注意的是，作为副产品，在建筑物的新视角合成方面也获得了额外的提升。
英文摘要：
Over the last few decades, image-based building surface reconstruction has garnered substantial research interest and has been applied across various fields, such as heritage preservation, architectural planning, etc. Compared to the traditional photogrammetric and NeRF-based solutions, recently, Gaussian fields-based methods have exhibited significant potential in generating surface meshes due to their time-efficient training and detailed 3D information preservation. However, most gaussian fields-based methods are trained with all image pixels, encompassing building and nonbuilding areas, which results in a significant noise for building meshes and degeneration in time efficiency. This paper proposes a novel framework, Masked Gaussian Fields (MGFs), designed to generate accurate surface reconstruction for building in a time-efficient way. The framework first applies EfficientSAM and COLMAP to generate multi-level masks of building and the corresponding masked point clouds. Subsequently, the masked gaussian fields are trained by integrating two innovative losses: a multi-level perceptual masked loss focused on constructing building regions and a boundary loss aimed at enhancing the details of the boundaries between different masks. Finally, we improve the tetrahedral surface mesh extraction method based on the masked gaussian spheres. Comprehensive experiments on UAV images demonstrate that, compared to the traditional method and several NeRF-based and Gaussian-based SOTA solutions, our approach significantly improves both the accuracy and efficiency of building surface reconstruction. Notably, as a byproduct, there is an additional gain in the novel view synthesis of building.
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。
