# Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry

arXiv: https://arxiv.org/abs/1904.01892 · HTML: https://mlsanity.com/paper/1904.01892/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 27 of 27)

- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (2021)
- [Generalizing to the Open World: Deep Visual Odometry with Online Adaptation](https://mlsanity.com/paper/2103.15279/) (2021)
- [Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection](https://mlsanity.com/paper/2205.06187/) (2022)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals](https://mlsanity.com/paper/2104.06789/) (2021)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Deep Visual Odometry with Events and Frames](https://mlsanity.com/paper/2309.09947/) (2023)
- [4DRVO-Net: Deep 4D Radar-Visual Odometry Using Multi-Modal and Multi-Scale Adaptive Fusion](https://mlsanity.com/paper/2308.06573/) (2023)
- [Self-supervised Visual-LiDAR Odometry with Flip Consistency](https://mlsanity.com/paper/2101.01322/) (2021)
- [Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World](https://mlsanity.com/paper/2203.05712/) (2022)
- [Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth](https://mlsanity.com/paper/2203.01557/) (2022)
- [EMA-VIO: Deep Visual-Inertial Odometry with External Memory Attention](https://mlsanity.com/paper/2209.08490/) (2022)
- [Temporal Point Cloud Completion with Pose Disturbance](https://mlsanity.com/paper/2202.03084/) (2022)
- [Information-Theoretic Odometry Learning](https://mlsanity.com/paper/2203.05724/) (2022)
- [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)
- [Pseudo-LiDAR for Visual Odometry](https://mlsanity.com/paper/2209.01567/) (2022)
- [CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose](https://mlsanity.com/paper/2212.05845/) (2022)
- [UNO: Unified Self-Supervised Monocular Odometry for Platform-Agnostic Deployment](https://mlsanity.com/paper/2506.07013/) (2025)
- [Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment](https://mlsanity.com/paper/2210.00413/) (2022)
- [A survey on deep learning approaches for data integration in autonomous driving system](https://mlsanity.com/paper/2306.11740/) (2023)
- [Deep auxiliary learning for visual localization using colorization task](https://mlsanity.com/paper/2107.00222/) (2021)
- [Dense Depth Estimation from Multiple 360-degree Images Using Virtual Depth](https://mlsanity.com/paper/2112.14931/) (2021)
- [SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery](https://mlsanity.com/paper/2211.08904/) (2022)
- [Brain-Inspired Visual Odometry: Balancing Speed and Interpretability through a System of Systems Approach](https://mlsanity.com/paper/2312.13162/) (2023)
- [PRAM: Place Recognition Anywhere Model for Efficient Visual Localization](https://mlsanity.com/paper/2404.07785/) (2024)
- [Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graph](https://mlsanity.com/paper/2408.15750/) (2024)

## Abstract (arXiv)

Most previous learning-based visual odometry (VO) methods take VO as a pure tracking problem. In contrast, we present a VO framework by incorporating two additional components called Memory and Refining. The Memory component preserves global information by employing an adaptive and efficient selection strategy. The Refining component ameliorates previous results with the contexts stored in the Memory by adopting a spatial-temporal attention mechanism for feature distilling. Experiments on the KITTI and TUM-RGBD benchmark datasets demonstrate that our method outperforms state-of-the-art learning-based methods by a large margin and produces competitive results against classic monocular VO approaches. Especially, our model achieves outstanding performance in challenging scenarios such as texture-less regions and abrupt motions, where classic VO algorithms tend to fail.