解决遥感影像跨季节立体匹配难题，实现多年份影像的精准三维重建。
Diachronic Stereo Matching for Multi-Date Satellite Imagery
- 基于单目深度先验微调深度立体网络，适应时间跨度大的影像对。
- 在跨季节、光照变化显著的图像对上，几何误差降至1.23米。
- 适用于多年份卫星影像重建，尤其适合季节差异大的场景。
近年来，基于图像的卫星三维重建沿两个互补方向发展：一方面，多时相方法结合NeRF或高斯泼溅，利用大量观测数据实现高精度重建；另一方面，经典立体重建流程对同时或准同时图像对表现稳健且可扩展。然而，当两幅图像拍摄间隔数月时，强烈的季节、光照和阴影变化违背了标准立体假设，导致现有流程失效。本文提出首个针对遥感影像的跨时相立体匹配方法，首次实现远距离时间配对影像的可靠三维重建。核心创新在于：(1) 利用单目深度先验微调先进深度立体网络，(2) 在专门构建的包含多样跨时相图像对的数据集上训练。我们从预训练的MonSter模型出发，该模型初始在SceneFlow和KITTI等合成与真实数据集上训练，再在来自DFC2019遥感挑战赛的立体对上进行微调，涵盖不同季节与光照条件下的同步与跨时相配对。在多时相WorldView-3影像上的实验表明，本方法在同步与跨时相设置下均优于经典流程及未适配的深度立体模型。在时间多样的图像上微调并结合单目先验，是实现此前不可兼容采集时间三维重建的关键。图1展示奥马哈（OMA 331测试场景）冬-秋图像对的数字表面模型结果：我们的方法在强烈外观变化下仍能恢复准确几何结构，而零样本方法失败；黑框为视角遮挡导致的缺失值。括号内为平均高程误差，越低越好，本方法为1.23米，零样本为3.99米。
原文摘要 · Abstract (English)
Recent advances in image-based satellite 3D reconstruction have progressed along two complementary directions. On one hand, multi-date approaches using NeRF or Gaussian-splatting jointly model appearance and geometry across many acquisitions, achieving accurate reconstructions on opportunistic imagery with numerous observations. On the other hand, classical stereoscopic reconstruction pipelines deliver robust and scalable results for simultaneous or quasi-simultaneous image pairs. However, when the two images are captured months apart, strong seasonal, illumination, and shadow changes violate standard stereoscopic assumptions, causing existing pipelines to fail. This work presents the first Diachronic Stereo Matching method for satellite imagery, enabling reliable 3D reconstruction from temporally distant pairs. Two advances make this possible: (1) fine-tuning a state-of-the-art deep stereo network that leverages monocular depth priors, and (2) exposing it to a dataset specifically curated to include a diverse set of diachronic image pairs. In particular, we start from a pretrained MonSter model, trained initially on a mix of synthetic and real datasets such as SceneFlow and KITTI, and fine-tune it on a set of stereo pairs derived from the DFC2019 remote sensing challenge. This dataset contains both synchronic and diachronic pairs under diverse seasonal and illumination conditions. Experiments on multi-date WorldView-3 imagery demonstrate that our approach consistently surpasses classical pipelines and unadapted deep stereo models on both synchronic and diachronic settings. Fine-tuning on temporally diverse images, together with monocular priors, proves essential for enabling 3D reconstruction from previously incompatible acquisition dates. Left image (winter) Right image (autumn) DSM geometry Ours (1.23 m) Zero-shot (3.99 m) LiDAR GT Figure 1. Output geometry for a winter-autumn image pair from Omaha (OMA 331 test scene). Our method recovers accurate geometry despite the diachronic nature of the pair, exhibiting strong appearance changes, which cause existing zero-shot methods to fail. Missing values due to perspective shown in black. Mean altitude error in parentheses; lower is better.
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。