# RAM-VO: Less is more in Visual Odometry

arXiv: https://arxiv.org/abs/2107.02974 · HTML: https://mlsanity.com/paper/2107.02974/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 15 of 15)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (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)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Recurrent Models of Visual Attention](https://mlsanity.com/paper/1406.6247/) (2014)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Deep Auxiliary Learning for Visual Localization and Odometry](https://mlsanity.com/paper/1803.03642/) (2018)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Distilling Knowledge From a Deep Pose Regressor Network](https://mlsanity.com/paper/1908.00858/) (2019)
- [DeepVO: A Deep Learning approach for Monocular Visual Odometry](https://mlsanity.com/paper/1611.06069/) (2016)
- [SalientDSO: Bringing Attention to Direct Sparse Odometry](https://mlsanity.com/paper/1803.00127/) (2018)
- [Learning monocular visual odometry with dense 3D mapping from dense 3D flow](https://mlsanity.com/paper/1803.02286/) (2018)
- [Learning Monocular Visual Odometry through Geometry-Aware Curriculum Learning](https://mlsanity.com/paper/1903.10543/) (2019)
- [DPC-Net: Deep Pose Correction for Visual Localization](https://mlsanity.com/paper/1709.03128/) (2017)
- [Exploring Self-Attention for Visual Odometry](https://mlsanity.com/paper/2011.08634/) (2020)

## Abstract (arXiv)

Building vehicles capable of operating without human supervision requires the determination of the agent's pose. Visual Odometry (VO) algorithms estimate the egomotion using only visual changes from the input images. The most recent VO methods implement deep-learning techniques using convolutional neural networks (CNN) extensively, which add a substantial cost when dealing with high-resolution images. Furthermore, in VO tasks, more input data does not mean a better prediction; on the contrary, the architecture may filter out useless information. Therefore, the implementation of computationally efficient and lightweight architectures is essential. In this work, we propose the RAM-VO, an extension of the Recurrent Attention Model (RAM) for visual odometry tasks. RAM-VO improves the visual and temporal representation of information and implements the Proximal Policy Optimization (PPO) algorithm to learn robust policies. The results indicate that RAM-VO can perform regressions with six degrees of freedom from monocular input images using approximately 3 million parameters. In addition, experiments on the KITTI dataset demonstrate that RAM-VO achieves competitive results using only 5.7% of the available visual information.