# Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

arXiv: https://arxiv.org/abs/1902.09103 · HTML: https://mlsanity.com/paper/1902.09103/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 17 of 17)

- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments](https://mlsanity.com/paper/2312.09243/) (2023)
- [DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium](https://mlsanity.com/paper/2304.03560/) (2023)
- [3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video](https://mlsanity.com/paper/2112.03045/) (2021)
- [Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels](https://mlsanity.com/paper/2503.04079/) (2025)
- [SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning](https://mlsanity.com/paper/2407.05283/) (2024)
- [MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints](https://mlsanity.com/paper/2109.06768/) (2021)
- [Spherical formulation of geometric motion segmentation constraints in fisheye cameras](https://mlsanity.com/paper/2104.12404/) (2021)
- [Uncertainty-Driven Dense Two-View Structure from Motion](https://mlsanity.com/paper/2302.00523/) (2023)
- [On the Coupling of Depth and Egomotion Networks for Self-Supervised Structure from Motion](https://mlsanity.com/paper/2106.04007/) (2021)
- [RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry](https://mlsanity.com/paper/2203.07162/) (2022)
- [Pseudo-LiDAR for Visual Odometry](https://mlsanity.com/paper/2209.01567/) (2022)
- [Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D](https://mlsanity.com/paper/2108.01980/) (2021)
- [Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning](https://mlsanity.com/paper/2511.01502/) (2025)
- [Self-supervised Learning of Occlusion Aware Flow Guided 3D Geometry Perception with Adaptive Cross Weighted Loss from Monocular Videos](https://mlsanity.com/paper/2108.03893/) (2021)
- [SelfOdom: Self-supervised Egomotion and Depth Learning via Bi-directional Coarse-to-Fine Scale Recovery](https://mlsanity.com/paper/2211.08904/) (2022)
- [UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry](https://mlsanity.com/paper/2509.13713/) (2025)

## Abstract (arXiv)

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that jointly optimizes the relative pose and target image depth has attracted the attention of the community. Previous works rely on the photometric error generated from depths and poses between adjacent frames, which contains large systematic error under realistic scenes due to reflective surfaces and occlusions. In this paper, we bridge the gap between geometric loss and photometric loss by introducing the matching loss constrained by epipolar geometry in a self-supervised framework. Evaluated on the KITTI dataset, our method outperforms the state-of-the-art unsupervised ego-motion estimation methods by a large margin. The code and data are available at https://github.com/hlzz/DeepMatchVO.