Benefiting from the unprecedented technology development of sensors, platforms and algorithms for 3D data acquisition and generation, point clouds are becoming more significant and accessible than before. In addition to widely-used LiDAR point clouds, satellite stereo imagery- and InSAR- based 3D data also cannot be ignored since they can provide low-quality but global information. In order to overcome limitations of a single data source, fusing 3D point clouds from two or more sensors could be a solution. As an early attempt to study those spaceborne 3D data, we hope to develop effective methods for multisensory point cloud labeling.