# Aerial-Ground Image Feature Matching via 3D Gaussian Splatting-based Intermediate View Rendering

arXiv: https://arxiv.org/abs/2509.19898 · HTML: https://mlsanity.com/paper/2509.19898/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [ContextDesc: Local Descriptor Augmentation with Cross-Modality Context](https://mlsanity.com/paper/1904.04084/) (2019)
- [PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2410.22128/) (2024)
- [GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints](https://mlsanity.com/paper/1807.06294/) (2018)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [Leveraging Photogrammetric Mesh Models for Aerial-Ground Feature Point Matching Toward Integrated 3D Reconstruction](https://mlsanity.com/paper/2002.09085/) (2020)
- [Optimized Views Photogrammetry: Precision Analysis and A Large-scale Case Study in Qingdao](https://mlsanity.com/paper/2206.12216/) (2022)

## Built on by (most cited first, 3 of 3)

- [Object-Centric 3D Gaussian Splatting for Strawberry Plant Reconstruction and Phenotyping](https://mlsanity.com/paper/2511.02207/) (2025)
- [Robust structure from motion for aerial-ground images via detector-free feature matching and multi-view track refinement](https://mlsanity.com/paper/2608.15251/) (2026)
- [3D Gaussian Splatting for Fine-grained Urban Scene Reconstruction via Semantic-guided Density Control and Loss Design](https://mlsanity.com/paper/2610.16292/) (2026)

## Abstract (arXiv)

The integration of aerial and ground images has been a promising solution in 3D modeling of complex scenes, which is seriously restricted by finding reliable correspondences. The primary contribution of this study is a feature matching algorithm for aerial and ground images, whose core idea is to generate intermediate views to alleviate perspective distortions caused by the extensive viewpoint changes. First, by using aerial images only, sparse models are reconstructed through an incremental SfM (Structure from Motion) engine due to their large scene coverage. Second, 3D Gaussian Splatting is then adopted for scene rendering by taking as inputs sparse points and oriented images. For accurate view rendering, a render viewpoint determination algorithm is designed by using the oriented camera poses of aerial images, which is used to generate high-quality intermediate images that can bridge the gap between aerial and ground images. Third, with the aid of intermediate images, reliable feature matching is conducted for match pairs from render-aerial and render-ground images, and final matches can be generated by transmitting correspondences through intermediate views. By using real aerial and ground datasets, the validation of the proposed solution has been verified in terms of feature matching and scene rendering and compared comprehensively with widely used methods. The experimental results demonstrate that the proposed solution can provide reliable feature matches for aerial and ground images with an obvious increase in the number of initial and refined matches, and it can provide enough matches to achieve accurate ISfM reconstruction and complete 3DGS-based scene rendering.