We apply some state-of-the-art semantic segmentation methods to InSAR image building segmentation, directly. They are Unet, SegNet, RefineNet, PSPNet, and Deeplab v3+. These segmentation patterns are regarded as the comparative results with CVCMFFNet, which links to https://github.com/Jiankun-chen/CVCMFFNet-master

A pipeline to segment high-resolution point clouds representing urban environments into geometric primitives; we focus on planes, cylinders and spheres, which are the main features of buildings (walls, roofs, arches, ...) and ground surfaces (streets, pavements, platforms), and identify the unique parameters of each instance.