首个月球立体图像数据集，让深度模型学会在无纹理月面重建3D地形。
Adapting Stereo Vision From Objects To 3D Lunar Surface Reconstruction with the StereoLunar Dataset
- 用光线追踪生成高保真月球立体图像对，覆盖多样光照与视角。
- 在合成与真实月面数据上，3D重建精度显著优于零样本基线。
- 适合做月球探测、深空视觉的科研人员和工程团队参考。
精确的月球表面三维重建对太空探索至关重要。然而，现有立体视觉方法因月面缺乏纹理、光照变化剧烈及轨道轨迹特殊而表现不佳。当前主流深度学习模型多在人类尺度数据集上训练，极少在行星影像上测试，无法直接迁移至月球环境。为此，我们提出LunarStereo，首个基于高分辨率地形与反射率模型、通过光线追踪生成的月球逼真立体图像对数据集，覆盖南极区域多样高程、光照条件与观测角度，为三维重建任务提供物理可信的监督信号。基于该数据集，我们通过微调将MASt3R模型适配至月球场景。在合成与真实月面数据上进行广泛定性与定量实验，评估三维表面重建与相对位姿估计性能。结果表明，该方法显著优于零样本基线，推动了外星环境中跨尺度泛化的实现。
原文摘要 · Abstract (English)
Accurate 3D reconstruction of lunar surfaces is essential for space exploration. However, existing stereo vision reconstruction methods struggle in this context due to the Moon's lack of texture, difficult lighting variations, and atypical orbital trajectories. State-of-the-art deep learning models, trained on human-scale datasets, have rarely been tested on planetary imagery and cannot be transferred directly to lunar conditions. To address this issue, we introduce LunarStereo, the first open dataset of photorealistic stereo image pairs of the Moon, simulated using ray tracing based on high-resolution topography and reflectance models. It covers diverse altitudes, lighting conditions, and viewing angles around the lunar South Pole, offering physically grounded supervision for 3D reconstruction tasks. Based on this dataset, we adapt the MASt3R model to the lunar domain through fine-tuning on LunarStereo. We validate our approach through extensive qualitative and quantitative experiments on both synthetic and real lunar data, evaluating 3D surface reconstruction and relative pose estimation. Extensive experiments on synthetic and real lunar data validate the approach, demonstrating significant improvements over zero-shot baselines and paving the way for robust cross-scale generalization in extraterrestrial environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。