Abstract. Stereo vision has been proven to be an efficient tool for 3D reconstruction in lunar topographic mapping. However, point clouds reconstructed from pairs of stereo images always suffer from occlusions and illumination changes, especially in Lunar environments, resulting in incomplete geometric information. 3D point cloud completion is usually required for refining photogrammetric point clouds and enabling further applications. In this work, we address the problem of completing and refining 3D photogrammetric point clouds based on the assumption that 3D terrain should be continuous and with consistent slope change. We proposed a generalized strategy for 3D point cloud completion of lunar topographic mapping, including distance-weighted point cloud interpolation, terrian-continuous constrained outlier detection, and contour-based hole filling. We carried out experiments on two datasets of point clouds generated from 12 pairs and 6 pairs of stereo LROC NAC images covering the Apollo 17 and the Chang’E-4 landing sites, respectively. As a result, the holes in the initial DTM have been smoothly filled and the completeness of the whole DTM has been greatly improved. The incomplete area of the experimental areas has dropped by 100% and 93%, respectively. Finally, we constructed DTM with a resolution of 10 m covering a 33 km × 60 km area of the Apollo 17 landing site with RMSE of 4 m and a 12 km × 56 km area of Chang’E-4 landing site with RMSE of 4 m compared with LOLA laser points as a reference.