# RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training

arXiv: https://arxiv.org/abs/2202.12838 · HTML: https://mlsanity.com/paper/2202.12838/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 25 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [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)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [DSAC - Differentiable RANSAC for Camera Localization](https://mlsanity.com/paper/1611.05705/) (2016)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [Relative Camera Pose Estimation Using Convolutional Neural Networks](https://mlsanity.com/paper/1702.01381/) (2017)
- [RPNet: an End-to-End Network for Relative Camera Pose Estimation](https://mlsanity.com/paper/1809.08402/) (2018)
- [Deep Fundamental Matrix Estimation without Correspondences](https://mlsanity.com/paper/1810.01575/) (2018)

## Built on by (most cited first, 4 of 4)

- [Sensor Fusion by Spatial Encoding for Autonomous Driving](https://mlsanity.com/paper/2308.10707/) (2023)
- [A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective](https://mlsanity.com/paper/2211.10963/) (2022)
- [PoseViNet: Distracted Driver Action Recognition Framework Using Multi-View Pose Estimation and Vision Transformer](https://mlsanity.com/paper/2312.14577/) (2023)
- [Map-Free Visual Relocalization Enhanced by Instance Knowledge and Depth Knowledge](https://mlsanity.com/paper/2408.13085/) (2024)

## Abstract (arXiv)

Relative camera pose estimation, i.e. estimating the translation and rotation vectors using a pair of images taken in different locations, is an important part of systems in augmented reality and robotics. In this paper, we present an end-to-end relative camera pose estimation network using a siamese architecture that is independent of camera parameters. The network is trained using the Cambridge Landmarks data with four individual scene datasets and a dataset combining the four scenes. To improve generalization, we propose a novel two-stage training that alleviates the need of a hyperparameter to balance the translation and rotation loss scale. The proposed method is compared with one-stage training CNN-based methods such as RPNet and RCPNet and demonstrate that the proposed model improves translation vector estimation by 16.11%, 28.88%, and 52.27% on the Kings College, Old Hospital, and St Marys Church scenes, respectively. For proving texture invariance, we investigate the generalization of the proposed method augmenting the datasets to different scene styles, as ablation studies, using generative adversarial networks. Also, we present a qualitative assessment of epipolar lines of our network predictions and ground truth poses.