外观
论文arXiv 2610.0711023 天前
MoonGS：使用来自图像对的鲁棒深度特征通过 Gaussian Splatting 实现月表高质量表示
原文链接：MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs（arXiv 2610.07110 · 发布日期：2026-10-05）
MoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image Pairs
MoonGS面向稀疏月球车图像重建，利用两图像前馈预测3D Gaussian，并在月表基准、合成数据和嫦娥影像上验证。
核心要点
- 稀疏月球车图像因视角重叠不足、纹理弱和数据有限，难以高质量重建月表。
- 仅用两张输入图像，单次前向预测像素对齐Gaussian primitives，无需逐场景优化。
- 结合基础模型深度特征、语义先验和熵引导重采样，以增强弱纹理稀疏观测。
- 在LuSNAR和MoonBlender上优于前馈NeRF/3DGS基线；代码和数据集已公开。
验证范围与局限：验证包括LuSNAR基准、合成弱纹理MoonBlender数据集，以及嫦娥任务影像的定性评估。
英文摘要 (Abstract)
High-quality 3D reconstruction of lunar terrain from sparse rover images is indispensable for autonomous lunar exploration, but remains challenging because viewpoint overlap is insufficient, surface textures are weak, and data volume is limited. We propose MoonGS, the first feed-forward 3D Gaussian Splatting framework tailored to lunar scenes. Given only two input images, MoonGS predicts pixel-aligned Gaussian primitives in a single forward pass and renders photorealistic novel views without any per-scene optimization. MoonGS (i) adopts an adaptable backbone design that seamlessly integrates advanced vision foundation models to extract robust depth features; (ii) integrates semantic priors in two manners: merging semantic cues with visual features to refine Gaussian parameter estimation, and adopting a semantic ranking loss that regularizes background depth; and (iii) employs an entropy-guided heuristic resampling strategy to augment sparse observations by selecting the most informative distant viewpoints with negligible overhead. Experiments on the LuSNAR benchmark and our synthetic weak-texture MoonBlender dataset show that MoonGS surpasses state-of-the-art feed-forward NeRF/3DGS baselines by +4.9 dB PSNR, +0.29 SSIM, and 40% lower LPIPS while maintaining sub-second inference. Furthermore, we validate the broad applicability of our framework by demonstrating that it effectively leverages state-of-the-art backbones, including VGGT, to significantly boost performance. Qualitative evaluations on Chang'e mission imagery also show the best visual quality among compared methods, indicating robustness on real lunar data. The source code and dataset are publicly available at https://github.com/InRobots/MoonBlender.
作者：Yun Jiang, Zheng Bo, Yingying Zhang, Xueming Xiao, Tao Hu, Hutao Cui, Zhiguo Meng, Ke Gao, Yang Gao, Meibao Yao
来源
本页事实对应的公开页面，以原文为准。