发表机构
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MarsFM提出一种结合生成先验与立体几何及阴影约束的流匹配模型，用于从HiRISE图像估计火星地形，在低步推理下实现高精度。
AI 中文摘要
我们提出了MarsFM，一种基于图像条件的潜在流匹配模型，用于从单波段HiRISE RED正射影像中进行局部火星地形估计。该方法将预训练的生成先验与立体几何监督以及可微的月球-朗伯阴影目标相结合。地形、法线、梯度、曲率和序数项约束了地形结构的互补方面，而正仿射不变图像比较则约束了渲染外观。一项评估包含2024个按积分步数收集的补丁记录，在归一化符号对数地形空间中，一到二十步欧拉步长的平均仿射对齐RMSE在0.0935至0.0957之间。这些分数衡量了在正参考支持上与VAE重建参考的一致性。其狭窄范围支持该协议下的低步推理。空间、微分和光谱诊断显示了广泛的地形对应性，同时伴有平滑、振幅压缩和边界不匹配。MarsFM提供了一个将学习到的地形先验与基于图像的约束相结合的框架；建立改进的物理地形分辨率需要匹配的基线和独立的高分辨率参考数据。数据：此https URL 代码：此https URL。
英文摘要
We present MarsFM, an image-conditioned latent flow-matching model for local Martian relief estimation from single-band HiRISE RED orthoimagery. The method combines a pretrained generative prior with stereo-derived geometric supervision and a differentiable Lunar--Lambert shading objective. Relief, normal, gradient, curvature, and ordinal terms constrain complementary aspects of terrain structure, while a positive-affine-invariant image comparison constrains rendered appearance. An evaluation comprising 2024 gathered patch records per integration-step count yields mean affine-aligned RMSE between 0.0935 and 0.0957 in normalized signed-log relief space for one to twenty Euler steps. These scores measure agreement with VAE-reconstructed references on positive-reference support. Their narrow range supports low-step inference under this protocol. Spatial, differential, and spectral diagnostics show broad terrain correspondence alongside smoothing, amplitude compression, and boundary mismatch. MarsFM provides a framework for combining learned terrain priors with image-based constraints; establishing improved physical terrain resolution requires matched baselines and independent high-resolution reference data. Data: https://huggingface.co/datasets/SuperComputer/mars_hirise_dtm_processed-6aa9b66ba461e07f; code: https://github.com/Marius-Juston/MarsRecon.
Comments73 pages, 62 figures
