Diachronic Stereo Matching for Multi-Date Satellite Imagery

2026-01-30

AI Summary

This work addresses the failure of traditional stereo matching methods on cross-seasonal satellite imagery, where drastic changes in illumination and surface appearance severely degrade performance. To overcome this limitation, the authors propose the first temporal stereo matching approach tailored for multi-temporal remote sensing images. Their method fine-tunes a deep stereo network augmented with monocular depth priors, trained on the DFC2019 dataset containing both synchronous and asynchronous image pairs. By relaxing the conventional requirement of consistent imaging conditions, the proposed approach achieves a significant reduction in 3D reconstruction error—down to 1.23 meters on challenging WorldView-3 winter–autumn image pairs with strong appearance discrepancies—substantially outperforming classical pipelines and zero-shot deep models, which yield errors of 3.99 meters.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

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.

Problem

• Diachronic Stereo Matching
• Multi-Date Satellite Imagery
• 3D Reconstruction
• Temporal Appearance Change
• Stereo Matching

Innovation

• Diachronic Stereo Matching
• monocular depth priors
• multi-date satellite imagery
• 3D reconstruction
• deep stereo networks