# A Unified Benchmark and Modality-Adaptive Network for Day-and-Night Drone-View Geo-Localization

arXiv: https://arxiv.org/abs/2607.25778 · HTML: https://mlsanity.com/paper/2607.25778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 22 of 22)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation](https://mlsanity.com/paper/2303.11851/) (2023)
- [Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization](https://mlsanity.com/paper/2008.11646/) (2020)
- [Predicting Ground-Level Scene Layout from Aerial Imagery](https://mlsanity.com/paper/1612.02709/) (2016)
- [SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite](https://mlsanity.com/paper/2204.10704/) (2022)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [Vision-Based UAV Self-Positioning in Low-Altitude Urban Environments](https://mlsanity.com/paper/2201.09201/) (2022)
- [Game4Loc: A UAV Geo-Localization Benchmark from Game Data](https://mlsanity.com/paper/2409.16925/) (2024)
- [UAV-VisLoc: A Large-scale Dataset for UAV Visual Localization](https://mlsanity.com/paper/2405.11936/) (2024)
- [Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization](https://mlsanity.com/paper/2412.14819/) (2024)
- [MUST: The First Dataset and Unified Framework for Multispectral UAV Single Object Tracking](https://mlsanity.com/paper/2503.17699/) (2025)
- [Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization](https://mlsanity.com/paper/2502.11381/) (2025)
- [Object-aware graph matching network for cross-domain remote sensing image localization](https://mlsanity.com/paper/2511.02489/) (2025)
- [UniABG: Unified Adversarial View Bridging and Graph Correspondence for Unsupervised Cross-View Geo-Localization](https://mlsanity.com/paper/2511.12054/) (2025)
- [Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis](https://mlsanity.com/paper/2603.25819/) (2026)
- [Efficient Spike-driven Transformer for High-performance Drone-View Geo-Localization](https://mlsanity.com/paper/2512.19365/) (2025)
- [From Limited Labels to Open Domains:An Efficient Learning Method for Drone-view Geo-Localization](https://mlsanity.com/paper/2503.07520/) (2025)

## Abstract (arXiv)

Most existing drone-view geo-localization (DVGL) benchmarks contain drone imagery captured under a single illumination condition and lack geographically aligned visible drone images, infrared drone images, and satellite images from the same locations. To evaluate the generalization capability of DVGL methods under challenging illumination conditions, some methods train models on a visible benchmark and test them on an independent infrared benchmark. This protocol essentially constitutes transfer between datasets, which makes it difficult to systematically evaluate DVGL across daytime and nighttime conditions within a unified benchmark. To address this limitation, we construct IRCHN,a real-world DVGL benchmark designed for localization across different illumination conditions. IRCHN contains 26,460 images collected from 8,820 geographic locations across four representative scene categories, including farmland, coastline, forest, and urban areas. Each location provides one visible drone image, one infrared drone image, and one corresponding satellite image, which enables unified evaluation of DVGL methods across different illumination conditions and sensing modalities. We further propose the Modality-Adaptive State-Space Transport Relation Network (MASTR-Net), a DVGL framework tailored to localization under varying illumination conditions. MASTR-Net integrates modality-adaptive feature enhancement, bidirectional selective state-space relation modeling, and soft optimal transport relation alignment to jointly reduce modality gaps and view-induced structural discrepancies. Extensive experiments demonstrate that MASTR-Net outperforms existing state-of-the-art methods on IRCHN for localization under varying illumination conditions and achieves competitive performance on two infrared benchmarks, IR-VL328 and CVGL-RGBT. Code: https://github.com/SongtianhaoXu/MASTR-Net