English

MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints

Computer Vision and Pattern Recognition 2026-02-20 v4 Robotics

Abstract

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%.

Keywords

Cite

@article{arxiv.2109.06768,
  title  = {MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints},
  author = {Cong Wang and Yu-Ping Wang and Dinesh Manocha},
  journal= {arXiv preprint arXiv:2109.06768},
  year   = {2026}
}

Comments

Accepted by ICRA 2022

R2 v1 2026-06-24T05:57:33.485Z