# Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision

arXiv: https://arxiv.org/abs/2104.02538 · HTML: https://mlsanity.com/paper/2104.02538/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 74 references that are in the map.
- First posted on arXiv 6 Apr 2021.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Learning Convolutional Neural Networks for Graphs](https://mlsanity.com/paper/1605.05273/) (2016)
- [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)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC](https://mlsanity.com/paper/2002.12324/) (2020)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (2017)
- [Learning Less is More - 6D Camera Localization via 3D Surface Regression](https://mlsanity.com/paper/1711.10228/) (2017)
- [Image-based localization using LSTMs for structured feature correlation](https://mlsanity.com/paper/1611.07890/) (2016)
- [Modelling Uncertainty in Deep Learning for Camera Relocalization](https://mlsanity.com/paper/1509.05909/) (2015)
- [Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction](https://mlsanity.com/paper/2003.08802/) (2020)
- [Neural-Guided RANSAC: Learning Where to Sample Model Hypotheses](https://mlsanity.com/paper/1905.04132/) (2019)
- [AtLoc: Attention Guided Camera Localization](https://mlsanity.com/paper/1909.03557/) (2019)
- [Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network](https://mlsanity.com/paper/1707.09733/) (2017)
- [Expert Sample Consensus Applied to Camera Re-Localization](https://mlsanity.com/paper/1908.02484/) (2019)
- [Image-based Localization using Hourglass Networks](https://mlsanity.com/paper/1703.07971/) (2017)

## Built on by (most cited first, 30 of 37)

- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Poses](https://mlsanity.com/paper/2305.14059/) (2023)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [GLACE: Global Local Accelerated Coordinate Encoding](https://mlsanity.com/paper/2406.04340/) (2024)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [Camera Pose Auto-Encoders for Improving Pose Regression](https://mlsanity.com/paper/2207.05530/) (2022)
- [Bimodal Camera Pose Prediction for Endoscopy](https://mlsanity.com/paper/2204.04968/) (2022)
- [SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization](https://mlsanity.com/paper/2508.17972/) (2025)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [Coarse-to-Fine Multi-Scene Pose Regression with Transformers](https://mlsanity.com/paper/2308.11783/) (2023)
- [ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training](https://mlsanity.com/paper/2510.11605/) (2025)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [Leveraging Image Matching Toward End-to-End Relative Camera Pose Regression](https://mlsanity.com/paper/2211.14950/) (2022)
- [SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments](https://mlsanity.com/paper/2404.10527/) (2024)
- [A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features](https://mlsanity.com/paper/2510.00978/) (2025)
- [Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformer](https://mlsanity.com/paper/2512.21883/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [Learning to Localize in Unseen Scenes with Relative Pose Regressors](https://mlsanity.com/paper/2303.02717/) (2023)
- [OFVL-MS: Once for Visual Localization across Multiple Indoor Scenes](https://mlsanity.com/paper/2308.11928/) (2023)
- [NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People](https://mlsanity.com/paper/2410.18109/) (2024)
- [HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Dataset](https://mlsanity.com/paper/2303.02610/) (2023)
- [Bayesian inference and neural estimation of acoustic wave propagation](https://mlsanity.com/paper/2305.17749/) (2023)
- [VRS-NeRF: Visual Relocalization with Sparse Neural Radiance Field](https://mlsanity.com/paper/2404.09271/) (2024)
- [FaVoR: Features via Voxel Rendering for Camera Relocalization](https://mlsanity.com/paper/2409.07571/) (2024)
- [Graph Neural Networks for Jamming Source Localization](https://mlsanity.com/paper/2506.03196/) (2025)
- [ImLoc: Revisiting Visual Localization with Image-based Representation](https://mlsanity.com/paper/2601.04185/) (2026)
- [Global-Aware Edge Prioritization for Pose Graph Initialization](https://mlsanity.com/paper/2602.21963/) (2026)
- [Estimating Extreme 3D Image Rotation with Transformer Cross-Attention](https://mlsanity.com/paper/2303.02615/) (2023)

## Abstract (arXiv)

Visual re-localization means using a single image as input to estimate the camera's location and orientation relative to a pre-recorded environment. The highest-scoring methods are "structure based," and need the query camera's intrinsics as an input to the model, with careful geometric optimization. When intrinsics are absent, methods vie for accuracy by making various other assumptions. This yields fairly good localization scores, but the models are "narrow" in some way, eg., requiring costly test-time computations, or depth sensors, or multiple query frames. In contrast, our proposed method makes few special assumptions, and is fairly lightweight in training and testing. Our pose regression network learns from only relative poses of training scenes. For inference, it builds a graph connecting the query image to training counterparts and uses a graph neural network (GNN) with image representations on nodes and image-pair representations on edges. By efficiently passing messages between them, both representation types are refined to produce a consistent camera pose estimate. We validate the effectiveness of our approach on both standard indoor (7-Scenes) and outdoor (Cambridge Landmarks) camera re-localization benchmarks. Our relative pose regression method matches the accuracy of absolute pose regression networks, while retaining the relative-pose models' test-time speed and ability to generalize to non-training scenes.