# Self-Supervised Deep Visual Odometry with Online Adaptation

arXiv: https://arxiv.org/abs/2005.06136 · HTML: https://mlsanity.com/paper/2005.06136/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 May 2020.

## Built on by (most cited first, 30 of 35)

- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry](https://mlsanity.com/paper/2401.01887/) (2024)
- [Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction](https://mlsanity.com/paper/2103.16449/) (2021)
- [Demonstrating Agile Flight from Pixels without State Estimation](https://mlsanity.com/paper/2406.12505/) (2024)
- [DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environments](https://mlsanity.com/paper/2209.08430/) (2022)
- [Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation](https://mlsanity.com/paper/2111.04017/) (2021)
- [Interactron: Embodied Adaptive Object Detection](https://mlsanity.com/paper/2202.00660/) (2022)
- [Generalizing to the Open World: Deep Visual Odometry with Online Adaptation](https://mlsanity.com/paper/2103.15279/) (2021)
- [CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentation](https://mlsanity.com/paper/2303.10147/) (2023)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Continual BatchNorm Adaptation (CBNA) for Semantic Segmentation](https://mlsanity.com/paper/2203.01074/) (2022)
- [Self-supervised Visual-LiDAR Odometry with Flip Consistency](https://mlsanity.com/paper/2101.01322/) (2021)
- [Deep Online Correction for Monocular Visual Odometry](https://mlsanity.com/paper/2103.10029/) (2021)
- [Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World](https://mlsanity.com/paper/2203.05712/) (2022)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [MDN-VO: Estimating Visual Odometry with Confidence](https://mlsanity.com/paper/2112.12812/) (2021)
- [Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth](https://mlsanity.com/paper/2203.01557/) (2022)
- [Conformalized Multimodal Uncertainty Regression and Reasoning](https://mlsanity.com/paper/2309.11018/) (2023)
- [Learning Generalized Visual Odometry Using Position-Aware Optical Flow and Geometric Bundle Adjustment](https://mlsanity.com/paper/2111.11141/) (2021)
- [Temporal Point Cloud Completion with Pose Disturbance](https://mlsanity.com/paper/2202.03084/) (2022)
- [ZeroVO: Visual Odometry with Minimal Assumptions](https://mlsanity.com/paper/2506.08005/) (2025)
- [Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics](https://mlsanity.com/paper/2304.12289/) (2023)
- [UL-VIO: Ultra-lightweight Visual-Inertial Odometry with Noise Robust Test-time Adaptation](https://mlsanity.com/paper/2409.13106/) (2024)
- [On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion](https://mlsanity.com/paper/2106.04007/) (2021)
- [Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes](https://mlsanity.com/paper/2106.12958/) (2021)
- [Learning Interpretable BEV Based VIO without Deep Neural Networks](https://mlsanity.com/paper/2109.12292/) (2021)
- [CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose](https://mlsanity.com/paper/2212.05845/) (2022)
- [TIDE: Temporally Incremental Disparity Estimation via Pattern Flow in Structured Light System](https://mlsanity.com/paper/2310.08932/) (2023)
- [MODL: Multilearner Online Deep Learning](https://mlsanity.com/paper/2405.18281/) (2024)
- [An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World](https://mlsanity.com/paper/2504.11698/) (2025)

## Abstract (arXiv)

Self-supervised VO methods have shown great success in jointly estimating camera pose and depth from videos. However, like most data-driven methods, existing VO networks suffer from a notable decrease in performance when confronted with scenes different from the training data, which makes them unsuitable for practical applications. In this paper, we propose an online meta-learning algorithm to enable VO networks to continuously adapt to new environments in a self-supervised manner. The proposed method utilizes convolutional long short-term memory (convLSTM) to aggregate rich spatial-temporal information in the past. The network is able to memorize and learn from its past experience for better estimation and fast adaptation to the current frame. When running VO in the open world, in order to deal with the changing environment, we propose an online feature alignment method by aligning feature distributions at different time. Our VO network is able to seamlessly adapt to different environments. Extensive experiments on unseen outdoor scenes, virtual to real world and outdoor to indoor environments demonstrate that our method consistently outperforms state-of-the-art self-supervised VO baselines considerably.