# MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

arXiv: https://arxiv.org/abs/2109.06768 · HTML: https://mlsanity.com/paper/2109.06768/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 14 Sep 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [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)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras](https://mlsanity.com/paper/1904.04998/) (2019)
- [Self-Supervised Monocular Depth Hints](https://mlsanity.com/paper/1909.09051/) (2019)
- [TartanVO: A Generalizable Learning-based VO](https://mlsanity.com/paper/2011.00359/) (2020)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [Lightweight Probabilistic Deep Networks](https://mlsanity.com/paper/1805.11327/) (2018)
- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling](https://mlsanity.com/paper/2007.10983/) (2020)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation](https://mlsanity.com/paper/1902.09103/) (2019)
- [Guided Feature Selection for Deep Visual Odometry](https://mlsanity.com/paper/1811.09935/) (2018)
- [ORBBuf: A Robust Buffering Method for Remote Visual SLAM](https://mlsanity.com/paper/2010.14861/) (2020)

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

- [MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing](https://mlsanity.com/paper/2404.19026/) (2024)
- [Neural Point-based Volumetric Avatar: Surface-guided Neural Points for Efficient and Photorealistic Volumetric Head Avatar](https://mlsanity.com/paper/2307.05000/) (2023)
- [RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry](https://mlsanity.com/paper/2203.07162/) (2022)
- [LoLep: Single-View View Synthesis with Locally-Learned Planes and Self-Attention Occlusion Inference](https://mlsanity.com/paper/2307.12217/) (2023)
- [An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World](https://mlsanity.com/paper/2504.11698/) (2025)
- [Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning](https://mlsanity.com/paper/2511.01502/) (2025)

## Abstract (arXiv)

We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use an appropriate motion model that can help existing self-supervised monocular VO (SSM-VO) algorithms to overcome issues related to the local minima within their self-supervised loss functions. The motion model is expressed with a neural network named PPnet. It is trained to coarsely predict the next pose of the camera and the uncertainty of this prediction. Our self-supervised approach combines the original loss and the motion loss, which is the weighted difference between the prediction and the generated ego-motion. Taking two existing SSM-VO systems as our baseline, we evaluate our MotionHint algorithm on the standard KITTI benchmark. Experimental results show that our MotionHint algorithm can be easily applied to existing open-sourced state-of-the-art SSM-VO systems to greatly improve the performance by reducing the resulting ATE by up to 28.73%.