Aerial–Terrestrial Image Feature Matching: An Evaluation of Recent Deep Learning Methods
Wang Hui, Jiangxue Yu, San Jiang, Dejin Zhang, Qingquan Li · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · 2025
3D reconstruction of complex urban areas is becoming increasingly important in various applications. To achieve precise and complete 3D reconstruction, current approaches aim to combine aerial and terrestrial images. The main challenge is achieving reliable feature matching of aerial and terrestrial images under large viewing angles and varying scene illuminations. Traditional hand-crafted methods experience a significant decline in matching performance. In this context, deep learning-based feature matching methods have developed rapidly and gained extensive attention. However, their performance in handling challenging large-angle aerial-terrestrial datasets still needs to be evaluated. To assess their performance for aerial-terrestrial images, this study has reviewed and evaluated four types of recent deep learning-based feature matching networks and selected four sets of aerial-terrestrial datasets for experimental tests. Extensive experiments and evaluations have been conducted in terms of feature matching and image orientation based on SfM (Structure from Motion). The results demonstrate that GNN (Graph Neural Networks)-based methods and detectorfree methods exhibit significant advantages in feature matching of aerial-terrestrial datasets, which can generate effective and correct matches for aerial-terrestrial images with large scale and viewpoint differences. In particular, the combination of SuperPoint and LightGlue achieves the best performance, which can generate approximately ten times the number of aerial-terrestrial feature matches when compared with SIFT. In addition, all images can be registered in the SfM reconstruction using its matching results. However, the precision of deep learning-based methods is still inferior to the classical hand-crafted method in SfM reconstruction. Thus, there is still significant room for improvement to enhance their performance further.