# ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue

arXiv: https://arxiv.org/abs/2504.01261 · HTML: https://mlsanity.com/paper/2504.01261/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 2 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [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)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking](https://mlsanity.com/paper/1803.11285/) (2018)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System](https://mlsanity.com/paper/2408.03520/) (2024)
- [Search and Rescue under the Forest Canopy using Multiple UAVs](https://mlsanity.com/paper/1908.10541/) (2019)
- [LiDAR Odometry Survey: Recent Advancements and Remaining Challenges](https://mlsanity.com/paper/2312.17487/) (2023)
- [Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image](https://mlsanity.com/paper/2503.17358/) (2025)
- [Aerial Tensile Perching and Disentangling Mechanism for Long-Term Environmental Monitoring](https://mlsanity.com/paper/2403.01890/) (2024)
- [Scalable Outdoors Autonomous Drone Flight with Visual-Inertial SLAM and Dense Submaps Built without LiDAR](https://mlsanity.com/paper/2403.09596/) (2024)
- [Visual Appearance Analysis of Forest Scenes for Monocular SLAM](https://mlsanity.com/paper/1907.02824/) (2019)

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

- [Learning Agile Tensile Perching for Aerial Robots from Demonstrations](https://mlsanity.com/paper/2507.06172/) (2025)
- [VISTA: Monocular Segmentation-Based Mapping for Appearance and View-Invariant Global Localization](https://mlsanity.com/paper/2507.11653/) (2025)
- [Where to Perch in a Tree: Vision-Guidance for Tree-Grasping Drones](https://mlsanity.com/paper/2605.15430/) (2026)

## Abstract (arXiv)

Recent advancements in visual odometry systems have improved autonomous navigation; however, challenges persist in complex environments like forests, where dense foliage, variable lighting, and repetitive textures compromise feature correspondence accuracy. To address these challenges, we introduce ForestGlue, enhancing the SuperPoint feature detector through four configurations - grayscale, RGB, RGB-D, and stereo-vision - optimised for various sensing modalities. For feature matching, we employ LightGlue or SuperGlue, retrained with synthetic forest data. ForestGlue achieves comparable pose estimation accuracy to baseline models but requires only 512 keypoints - just 25% of the baseline's 2048 - to reach an LO-RANSAC AUC score of 0.745 at a 10deg threshold. With only a quarter of keypoints needed, ForestGlue significantly reduces computational overhead, demonstrating effectiveness in dynamic forest environments, and making it suitable for real-time deployment on resource-constrained platforms. By combining ForestGlue with a transformer-based pose estimation model, we propose ForestVO, which estimates relative camera poses using matched 2D pixel coordinates between frames. On challenging TartanAir forest sequences, ForestVO achieves an average relative pose error (RPE) of 1.09 m and a kittiscore of 2.33%, outperforming direct-based methods like DSO by 40% in dynamic scenes. Despite using only 10% of the dataset for training, ForestVO maintains competitive performance with TartanVO while being a significantly lighter model. This work establishes an end-to-end deep learning pipeline specifically tailored for visual odometry in forested environments, leveraging forest-specific training data to optimise feature correspondence and pose estimation, thereby enhancing the accuracy and robustness of autonomous navigation systems.