Relative Camera Pose Estimation Using Convolutional Neural Networks
Not on the map. Why?
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.
Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Feb 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 9; 2022: 14; 2023: 10; 2024: 7; 2025: 4; 2026: 3.
47 papers.
Sort:
By area:
- 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
- 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
- 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
- 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
- 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
- 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
- 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
- 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
- 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
- 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
- 2023Tame a Wild Camera: In-the-Wild Monocular Camera Calibrationcited by 34
35 more
- 2021Self-supervised Geometric Perceptioncited by 26
- 2023Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotationcited by 18
- 2021UAV Localization Using Autoencoded Satellite Imagescited by 17
- 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transformscited by 17
- 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
- 2021Wide-Baseline Multi-Camera Calibration using Person Re-Identificationcited by 15
- 2023ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Modelscited by 8
- 2023Lazy Visual Localization via Motion Averagingcited by 8
- 2022A Critical Analysis of Image-based Camera Pose Estimation Techniquescited by 7
- 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
- 2021LIFE: Lighting Invariant Flow Estimationcited by 6
- 2022Leveraging Image Matching Toward End-to-End Relative Camera Pose Regressioncited by 6
- 2024Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Camerascited by 6
- 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
- 2025GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representationscited by 5
- 2021Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavitiescited by 4
- 2022RelMobNet: End-to-end relative camera pose estimation using a robust two-stage trainingcited by 4
- 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
- 2021CNN-based Ego-Motion Estimation for Fast MAV Maneuverscited by 3
- 2022D-InLoc++: Indoor Localization in Dynamic Environmentscited by 2
- 2023CGA-PoseNet: Camera Pose Regression via a 1D-Up Approach to Conformal Geometric Algebracited by 2
- 2022Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimationcited by 1
- 2022Self-supervised Wide Baseline Visual Servoing via 3D Equivariancecited by 1
- 2022A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objectivecited by 1
- 2023Self-supervised learning of object pose estimation using keypoint predictioncited by 1
- 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
- 2025LiFMCR: Dataset and Benchmark for Light Field Multi-Camera Registrationcited by 1
- 2022Error-Covariance Analysis of Monocular Pose Estimation Using Total Least Squarescited by 0
- 2022Multi-task Learning for Camera Calibrationcited by 0
- 2023EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Imagescited by 0
- 2024Leveraging Spatial Attention and Edge Context for Optimized Feature Selection in Visual Localizationcited by 0
- 2025The Overlooked Value of Test-time Reference Sets in Visual Place Recognitioncited by 0
- 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1cited by 0
- 2026InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Datasetcited by 0
- 2026Relational Epipolar Graphs for Robust Relative Camera Pose Estimationcited by 0
- 2026Relational Epipolar Graphs for Robust Relative Camera Pose Estimation6 Apr 2026
- 2026InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset4 Apr 2026
- 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v120 Mar 2026
- 2025LiFMCR: Dataset and Benchmark for Light Field Multi-Camera Registration15 Oct 2025
- 2025The Overlooked Value of Test-time Reference Sets in Visual Place Recognition4 Oct 2025
- 2025GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations25 Aug 2025
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025
- 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching24 Nov 2024
- 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting29 Oct 2024
- 2024Leveraging Spatial Attention and Edge Context for Optimized Feature Selection in Visual Localization16 Oct 2024
- 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypoints11 Jul 2024
- 2024Extreme Two-View Geometry From Object Poses with Diffusion Models5 Feb 2024
35 more
- 2024Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras28 Jan 2024
- 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos23 Jan 2024
- 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs12 Dec 2023
- 2023EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Images16 Oct 2023
- 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon28 Sep 2023
- 2023Lazy Visual Localization via Motion Averaging19 Jul 2023
- 2023ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models29 Jun 2023
- 2023Tame a Wild Camera: In-the-Wild Monocular Camera Calibration19 Jun 2023
- 2023RelPose++: Recovering 6D Poses from Sparse-view Observations8 May 2023
- 2023Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation20 Mar 2023
- 2023Self-supervised learning of object pose estimation using keypoint prediction14 Feb 2023
- 2023CGA-PoseNet: Camera Pose Regression via a 1D-Up Approach to Conformal Geometric Algebra10 Feb 2023
- 2022Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression27 Nov 2022
- 2022Multi-task Learning for Camera Calibration22 Nov 2022
- 2022SPARF: Neural Radiance Fields from Sparse and Noisy Poses21 Nov 2022
- 2022A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective20 Nov 2022
- 2022Error-Covariance Analysis of Monocular Pose Estimation Using Total Least Squares21 Oct 2022
- 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Image11 Oct 2022
- 2022D-InLoc++: Indoor Localization in Dynamic Environments21 Sep 2022
- 2022Self-supervised Wide Baseline Visual Servoing via 3D Equivariance12 Sep 2022
- 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs18 Aug 2022
- 2022Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation18 Aug 2022
- 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild11 Aug 2022
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers18 Mar 2022
- 2022RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training25 Feb 2022
- 2022A Critical Analysis of Image-based Camera Pose Estimation Techniques15 Jan 2022
- 2021Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities13 Jul 2021
- 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learning7 Jun 2021
- 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms29 May 2021
- 2021Extreme Rotation Estimation using Dense Correlation Volumes28 Apr 2021
- 2021Wide-Baseline Multi-Camera Calibration using Person Re-Identification17 Apr 2021
- 2021LIFE: Lighting Invariant Flow Estimation7 Apr 2021
- 2021Self-supervised Geometric Perception4 Mar 2021
- 2021UAV Localization Using Autoencoded Satellite Images10 Feb 2021
- 2021CNN-based Ego-Motion Estimation for Fast MAV Maneuvers6 Jan 2021
- 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
- 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
- 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
- 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
- 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
- 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
- 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
- 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
- 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
- 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
- 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
- 2023Tame a Wild Camera: In-the-Wild Monocular Camera Calibrationcited by 34
12 most cited of 45 All 45 (JSON)
- 2026Relational Epipolar Graphs for Robust Relative Camera Pose Estimation6 Apr 2026
- 2026InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset4 Apr 2026
- 2026IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v120 Mar 2026
- 2025LiFMCR: Dataset and Benchmark for Light Field Multi-Camera Registration15 Oct 2025
- 2025The Overlooked Value of Test-time Reference Sets in Visual Place Recognition4 Oct 2025
- 2025GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations25 Aug 2025
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025
- 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching24 Nov 2024
- 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting29 Oct 2024
- 2024Leveraging Spatial Attention and Edge Context for Optimized Feature Selection in Visual Localization16 Oct 2024
- 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypoints11 Jul 2024
- 2024Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras28 Jan 2024
12 newest of 45 All 45 (JSON)