# Relative Camera Pose Estimation Using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1702.01381 · HTML: https://mlsanity.com/paper/1702.01381/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2017.

## Built on by (most cited first, 30 of 47)

- [SPARF: Neural Radiance Fields from Sparse and Noisy Poses](https://mlsanity.com/paper/2211.11738/) (2022)
- [RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos](https://mlsanity.com/paper/2401.12592/) (2024)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)
- [ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers](https://mlsanity.com/paper/2203.10157/) (2022)
- [PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2410.22128/) (2024)
- [Wide-Baseline Relative Camera Pose Estimation with Directional Learning](https://mlsanity.com/paper/2106.03336/) (2021)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs](https://mlsanity.com/paper/2208.08988/) (2022)
- [Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs](https://mlsanity.com/paper/2312.07246/) (2023)
- [Tame a Wild Camera: In-the-Wild Monocular Camera Calibration](https://mlsanity.com/paper/2306.10988/) (2023)
- [Self-supervised Geometric Perception](https://mlsanity.com/paper/2103.03114/) (2021)
- [UAV Localization Using Autoencoded Satellite Images](https://mlsanity.com/paper/2102.05692/) (2021)
- [Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation](https://mlsanity.com/paper/2303.11329/) (2023)
- [Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms](https://mlsanity.com/paper/2105.14246/) (2021)
- [End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon](https://mlsanity.com/paper/2309.16634/) (2023)
- [Wide-Baseline Multi-Camera Calibration using Person Re-Identification](https://mlsanity.com/paper/2104.08568/) (2021)
- [ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models](https://mlsanity.com/paper/2306.17140/) (2023)
- [Lazy Visual Localization via Motion Averaging](https://mlsanity.com/paper/2307.09981/) (2023)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [LIFE: Lighting Invariant Flow Estimation](https://mlsanity.com/paper/2104.03097/) (2021)
- [Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression](https://mlsanity.com/paper/2211.14950/) (2022)
- [Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras](https://mlsanity.com/paper/2401.15616/) (2024)
- [SRPose: Two-view Relative Pose Estimation with Sparse Keypoints](https://mlsanity.com/paper/2407.08199/) (2024)
- [GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations](https://mlsanity.com/paper/2508.18242/) (2025)
- [Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities](https://mlsanity.com/paper/2107.05789/) (2021)
- [RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training](https://mlsanity.com/paper/2202.12838/) (2022)
- [Extreme Two-View Geometry From Object Poses with Diffusion Models](https://mlsanity.com/paper/2402.02800/) (2024)

## Abstract (arXiv)

This paper presents a convolutional neural network based approach for estimating the relative pose between two cameras. The proposed network takes RGB images from both cameras as input and directly produces the relative rotation and translation as output. The system is trained in an end-to-end manner utilising transfer learning from a large scale classification dataset. The introduced approach is compared with widely used local feature based methods (SURF, ORB) and the results indicate a clear improvement over the baseline. In addition, a variant of the proposed architecture containing a spatial pyramid pooling (SPP) layer is evaluated and shown to further improve the performance.