MCTED：一个面向机器学习、用于从火星影像生成数字高程模型的数据集
MCTED: A Machine-Learning-Ready Dataset for Digital Elevation Model Generation From Mars Imagery
AI总结：
本文提出面向火星高程预测的机器学习数据集 MCTED，包含 80,898 个经清洗和掩码标注的 CTX 影像-DEM 样本，并证明在其上训练的小型 U-Net 可超越 DepthAnythingV2 的零样本性能。
摘要：
本工作提出了一个用于火星数字高程模型预测任务的新数据集，可供机器学习应用直接使用，称为 MCTED。该数据集通过一套综合处理流程生成，该流程用于处理来自 Day 等人的高分辨率火星正射影像与 DEM 配对数据，最终得到包含 80,898 个数据样本的数据集。源图像由火星勘测轨道飞行器使用 CTX 仪器采集，提供了对火星表面非常多样且全面的覆盖。考虑到大规模 DEM 所使用的处理流程较为复杂，原始数据中往往存在伪影和缺失数据点，为此我们开发了相应工具来解决或减轻其影响。我们将处理后的样本划分为训练集和验证集，并确保两个划分中的样本不覆盖任何相互重叠的区域，以避免数据泄漏。数据集中的每个样本都由光学影像块、DEM 块以及两个掩码块表示，掩码块用于指示原本缺失或由我们修改过的数值。这使得该数据集的未来使用者可以按自己的方式处理被修改过的高程区域。我们提供了所生成数据集的统计信息，包括样本的空间分布、高程值分布、坡度分布等。最后，我们在 MCTED 数据集上训练了一个小型 U-Net 架构，并将其在海拔预测任务上的性能与单目深度估计基础模型 DepthAnythingV2 进行比较。我们发现，即使是在该数据集上专门训练的一个非常小的架构，也能超过 DepthAnythingV2 这类深度估计基础模型的零样本性能。我们将该数据集及其生成所使用的代码完全开源在公共代码仓库中。
英文摘要：
This work presents a new dataset for the Martian digital elevation model prediction task, ready for machine learning applications called MCTED. The dataset has been generated using a comprehensive pipeline designed to process high-resolution Mars orthoimage and DEM pairs from Day et al., yielding a dataset consisting of 80,898 data samples. The source images are data gathered by the Mars Reconnaissance Orbiter using the CTX instrument, providing a very diverse and comprehensive coverage of the Martian surface. Given the complexity of the processing pipelines used in large-scale DEMs, there are often artefacts and missing data points in the original data, for which we developed tools to solve or mitigate their impact. We divide the processed samples into training and validation splits, ensuring samples in both splits cover no mutual areas to avoid data leakage. Every sample in the dataset is represented by the optical image patch, DEM patch, and two mask patches, indicating values that were originally missing or were altered by us. This allows future users of the dataset to handle altered elevation regions as they please. We provide statistical insights of the generated dataset, including the spatial distribution of samples, the distributions of elevation values, slopes and more. Finally, we train a small U-Net architecture on the MCTED dataset and compare its performance to a monocular depth estimation foundation model, DepthAnythingV2, on the task of elevation prediction. We find that even a very small architecture trained on this dataset specifically, beats a zero-shot performance of a depth estimation foundation model like DepthAnythingV2. We make the dataset and code used for its generation completely open source in public repositories.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
