# Last-Meter Precision Navigation for UAVs: A Diffusion-Refined Aerial Visual Servoing Approach

arXiv: https://arxiv.org/abs/2607.04352 · HTML: https://mlsanity.com/paper/2607.04352/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 5 Jul 2026.

## Builds on (most cited first, 30 of 30)

- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [RoboTHOR: An Open Simulation-to-Real Embodied AI Platform](https://mlsanity.com/paper/2004.06799/) (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)
- [Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching](https://mlsanity.com/paper/2005.03860/) (2020)
- [AerialVLN: Vision-and-Language Navigation for UAVs](https://mlsanity.com/paper/2308.06735/) (2023)
- [Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation](https://mlsanity.com/paper/2303.11851/) (2023)
- [UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles](https://mlsanity.com/paper/2104.00946/) (2021)
- [Optimal Feature Transport for Cross-View Image Geo-Localization](https://mlsanity.com/paper/1907.05021/) (2019)
- [Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image](https://mlsanity.com/paper/2204.04752/) (2022)
- [Unsupervised Scene Adaptation with Memory Regularization in vivo](https://mlsanity.com/paper/1912.11164/) (2019)
- [Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer](https://mlsanity.com/paper/2307.08015/) (2023)
- [Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching](https://mlsanity.com/paper/2203.14148/) (2022)
- [Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching](https://mlsanity.com/paper/2311.12751/) (2023)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents](https://mlsanity.com/paper/2508.00288/) (2025)
- [CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization](https://mlsanity.com/paper/2208.03660/) (2022)
- [Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models](https://mlsanity.com/paper/2504.10041/) (2025)
- [Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization](https://mlsanity.com/paper/2309.15556/) (2023)
- [Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization](https://mlsanity.com/paper/2211.05296/) (2022)
- [Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization](https://mlsanity.com/paper/2411.13610/) (2024)
- [Guided Attention Network for Object Detection and Counting on Drones](https://mlsanity.com/paper/1909.11307/) (2019)
- [Eye in the Sky: Drone-Based Object Tracking and 3D Localization](https://mlsanity.com/paper/1910.08259/) (2019)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Anomaly Detection in Aerial Videos with Transformers](https://mlsanity.com/paper/2209.13363/) (2022)
- [The Urban Last Mile Problem: Autonomous Drone Delivery to Your Balcony](https://mlsanity.com/paper/1809.08022/) (2018)

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

- [Uncertainty-Aware World Model for Aerial Image-Goal Navigation](https://mlsanity.com/paper/2608.05597/) (2026)
- [RASR: Range-Aware Scale Recovery for Metric UAV Navigation](https://mlsanity.com/paper/2607.09815/) (2026)
- [PACE: Polar Axis-Conditioned Estimation for PairUAV Relative Localization](https://mlsanity.com/paper/2607.17268/) (2026)

## Abstract (arXiv)

In this work, we study the last-meter precision navigation for UAVs, e.g., autonomously reaching a target within the final 10 meters using monocular vision. This task is challenging due to scale ambiguity, rotation discontinuities, and the need for fine-grained spatial reasoning. Existing methods often fail under large viewpoint changes or lack generalization to unseen environments. To this end, we propose DreamNav, a coarse-to-fine diffusion-refined aerial visual servoing framework. In the first coarse-estimation stage, a robust regression policy employs a trigonometric parameterization to predict rotation by jointly modeling sine and cosine components, effectively mitigating optimization instabilities caused by angular periodicity. Given this coarse estimate, the second diffusion-refined stage utilizes a pre-trained world model to simulate future visual observations for candidate actions, selecting the trajectory that minimizes visual discrepancy with the target through a process of visual imagination. To support rigorous evaluation, we contribute PairUAV, a large-scale benchmark comprising 4.8 million image pairs across 72 scenes, curated from the University-1652 dataset. Extensive experiments show DreamNav outperforms strong visual servoing and foundation model baselines in accuracy and generalization, with zero-shot transfer to unseen scenes.