# MDN-VO: Estimating Visual Odometry with Confidence

arXiv: https://arxiv.org/abs/2112.12812 · HTML: https://mlsanity.com/paper/2112.12812/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 40 references that are in the map.
- First posted on arXiv 23 Dec 2021.

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

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [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)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [Self-Supervised Deep Visual Odometry with Online Adaptation](https://mlsanity.com/paper/2005.06136/) (2020)
- [A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence](https://mlsanity.com/paper/2006.12567/) (2020)
- [Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas](https://mlsanity.com/paper/2009.02672/) (2020)
- [DeepVO: A Deep Learning approach for Monocular Visual Odometry](https://mlsanity.com/paper/1611.06069/) (2016)
- [Learning monocular visual odometry with dense 3D mapping from dense 3D flow](https://mlsanity.com/paper/1803.02286/) (2018)

## Built on by (most cited first, 6 of 6)

- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [Lightweight, Uncertainty-Aware Conformalized Visual Odometry](https://mlsanity.com/paper/2303.02207/) (2023)
- [Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach](https://mlsanity.com/paper/2305.06121/) (2023)
- [TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation](https://mlsanity.com/paper/2304.07728/) (2023)
- [ZeroVO: Visual Odometry with Minimal Assumptions](https://mlsanity.com/paper/2506.08005/) (2025)
- [AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation](https://mlsanity.com/paper/2206.12946/) (2022)

## Abstract (arXiv)

Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying on heuristic methods to detect failure. In this work, we propose a deep learning-based VO model to efficiently estimate 6-DoF poses, as well as a confidence model for these estimates. We utilise a CNN - RNN hybrid model to learn feature representations from image sequences. We then employ a Mixture Density Network (MDN) which estimates camera motion as a mixture of Gaussians, based on the extracted spatio-temporal representations. Our model uses pose labels as a source of supervision, but derives uncertainties in an unsupervised manner. We evaluate the proposed model on the KITTI and nuScenes datasets and report extensive quantitative and qualitative results to analyse the performance of both pose and uncertainty estimation. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases using the predicted pose uncertainty.