# SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery

arXiv: https://arxiv.org/abs/2211.08904 · HTML: https://mlsanity.com/paper/2211.08904/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 66 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints](https://mlsanity.com/paper/1802.05522/) (2018)
- [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)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [On-Manifold Preintegration for Real-Time Visual-Inertial Odometry](https://mlsanity.com/paper/1512.02363/) (2015)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)
- [VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem](https://mlsanity.com/paper/1701.08376/) (2017)
- [Excavating the Potential Capacity of Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2109.12484/) (2021)
- [Selective Sensor Fusion for Neural Visual-Inertial Odometry](https://mlsanity.com/paper/1903.01534/) (2019)
- [Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry](https://mlsanity.com/paper/1904.01892/) (2019)
- [SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation](https://mlsanity.com/paper/1911.09968/) (2019)
- [Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation](https://mlsanity.com/paper/2009.03787/) (2020)
- [Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation](https://mlsanity.com/paper/1902.09103/) (2019)
- [Learning Selective Sensor Fusion for States Estimation](https://mlsanity.com/paper/1912.13077/) (2019)
- [DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry](https://mlsanity.com/paper/2105.09899/) (2021)

## Abstract (arXiv)

Accurately perceiving location and scene is crucial for autonomous driving and mobile robots. Recent advances in deep learning have made it possible to learn egomotion and depth from monocular images in a self-supervised manner, without requiring highly precise labels to train the networks. However, monocular vision methods suffer from a limitation known as scale-ambiguity, which restricts their application when absolute-scale is necessary. To address this, we propose SelfOdom, a self-supervised dual-network framework that can robustly and consistently learn and generate pose and depth estimates in global scale from monocular images. In particular, we introduce a novel coarse-to-fine training strategy that enables the metric scale to be recovered in a two-stage process. Furthermore, SelfOdom is flexible and can incorporate inertial data with images, which improves its robustness in challenging scenarios, using an attention-based fusion module. Our model excels in both normal and challenging lighting conditions, including difficult night scenes. Extensive experiments on public datasets have demonstrated that SelfOdom outperforms representative traditional and learning-based VO and VIO models.