Lunar Terrain Modeling From Sparse Surface Points Using Signed Distance Fields and Dynamic Planar Features

Digital elevation models (DEMs) play a crucial role in scientific research and exploration missions of the lunar south pole regions, as they offer vital topographic and morphological information of terrain surfaces. Surface points processed from various remote sensors provide discrete but accurate measurements of lunar terrains. However, reconstructing high-resolution terrains from surface points poses significant challenges for neural networks primarily due to the lack of grid connectivity inherent in unordered surface points. Therefore, this study develops a point-based terrain reconstruction framework that incorporates learnable neural shape priors to better capture complex terrain geometry. To model structural characteristics inherent in 3-D surface points, a signed distance field (SDF) is introduced as a continuous representation of lunar surfaces. Moreover, we train a 3-D point-based encoder–decoder network that allows terrain modeling from unstructured surface points with encoded planar features. In addition, a dynamic planar features’ strategy is proposed to optimize the framework’s performance according to the characteristics of terrain flatness. Experiments were conducted on photoclinometry DEMs of the lunar polar region to demonstrate the advantages of our proposed framework. The qualitative and quantitative results highlight that our framework reconstructs accurate terrain geometry, outperforming traditional methods in terms of elevation, slope, aspect, and roughness. Furthermore, the model exhibits a generalization ability when applied to both lunar orbiter laser altimeter (LOLA) measurements and unseen regions, underscoring its effectiveness in lunar exploration tasks.