3-D Gaussian Splatting for Lunar Surface With Limited View Input

Accurate novel view synthesis of the lunar surface is critical for enhancing remote rover operation efficiency and supporting the creation of virtual environments for lunar exploration. Given the limited images captured by the lunar rover, we propose Moon-GS, a novel framework designed specifically for challenging lunar scenarios based on 3-D Gaussian splatting (3DGS). The core methodology involves initializing dense Gaussian primitives using pixel-wise feature matching to address sparse and incomplete point cloud issues, augmenting the training with virtual view constraints to propagate limited ground truth (GT) information across multiple perspectives, and employing geometric regularization strategies to ensure consistent 3-D representation. These innovations enable Moon-GS to model complex terrain with high fidelity, improve geometric consistency, and enhance rendering quality across unseen viewpoints. Experimental results on real and synthetic lunar datasets demonstrate its superiority over state-of-the-art (SOTA) methods in terms of rendering detail and structural integrity. This research offers a robust solution for lunar 3-D visualization, advancing the capabilities of remote rover operations and future exploration missions.