# Pose Graph Optimization for Unsupervised Monocular Visual Odometry

arXiv: https://arxiv.org/abs/1903.06315 · HTML: https://mlsanity.com/paper/1903.06315/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2019.

## Built on by (most cited first, 17 of 17)

- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [DF-VO: What Should Be Learnt for Visual Odometry?](https://mlsanity.com/paper/2103.00933/) (2021)
- [DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction](https://mlsanity.com/paper/2209.06351/) (2022)
- [LIFT-SLAM: a deep-learning feature-based monocular visual SLAM method](https://mlsanity.com/paper/2104.00099/) (2021)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2312.15268/) (2023)
- [DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry](https://mlsanity.com/paper/2105.09899/) (2021)
- [Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth](https://mlsanity.com/paper/2203.01557/) (2022)
- [Adversarial Attacks on Monocular Pose Estimation](https://mlsanity.com/paper/2207.07032/) (2022)
- [Monocular Depth Distribution Alignment with Low Computation](https://mlsanity.com/paper/2203.04538/) (2022)
- [RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry](https://mlsanity.com/paper/2203.07162/) (2022)
- [Pseudo-LiDAR for Visual Odometry](https://mlsanity.com/paper/2209.01567/) (2022)
- [HDPV-SLAM: Hybrid Depth-augmented Panoramic Visual SLAM for Mobile Mapping System with Tilted LiDAR and Panoramic Visual Camera](https://mlsanity.com/paper/2301.11823/) (2023)
- [A comparative evaluation of learned feature descriptors on hybrid monocular visual SLAM methods](https://mlsanity.com/paper/2104.00085/) (2021)
- [360 in the Wild: Dataset for Depth Prediction and View Synthesis](https://mlsanity.com/paper/2406.18898/) (2024)
- [Online Camera-to-ground Calibration for Autonomous Driving](https://mlsanity.com/paper/2303.17137/) (2023)
- [Joint Learning of Depth, Pose, and Local Radiance Field for Large Scale Monocular 3D Reconstruction](https://mlsanity.com/paper/2512.18237/) (2025)

## Abstract (arXiv)

Unsupervised Learning based monocular visual odometry (VO) has lately drawn significant attention for its potential in label-free leaning ability and robustness to camera parameters and environmental variations. However, partially due to the lack of drift correction technique, these methods are still by far less accurate than geometric approaches for large-scale odometry estimation. In this paper, we propose to leverage graph optimization and loop closure detection to overcome limitations of unsupervised learning based monocular visual odometry. To this end, we propose a hybrid VO system which combines an unsupervised monocular VO called NeuralBundler with a pose graph optimization back-end. NeuralBundler is a neural network architecture that uses temporal and spatial photometric loss as main supervision and generates a windowed pose graph consists of multi-view 6DoF constraints. We propose a novel pose cycle consistency loss to relieve the tensions in the windowed pose graph, leading to improved performance and robustness. In the back-end, a global pose graph is built from local and loop 6DoF constraints estimated by NeuralBundler and is optimized over SE(3). Empirical evaluation on the KITTI odometry dataset demonstrates that 1) NeuralBundler achieves state-of-the-art performance on unsupervised monocular VO estimation, and 2) our whole approach can achieve efficient loop closing and show favorable overall translational accuracy compared to established monocular SLAM systems.