# HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation

arXiv: https://arxiv.org/abs/2402.14371 · HTML: https://mlsanity.com/paper/2402.14371/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [Geometry-Aware Learning of Maps for Camera Localization](https://mlsanity.com/paper/1712.03342/) (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)
- [LENS: Localization enhanced by NeRF synthesis](https://mlsanity.com/paper/2110.06558/) (2021)
- [Learning Multi-Scene Absolute Pose Regression with Transformers](https://mlsanity.com/paper/2103.11468/) (2021)
- [AtLoc: Attention Guided Camera Localization](https://mlsanity.com/paper/1909.03557/) (2019)
- [DFNet: Enhance Absolute Pose Regression with Direct Feature Matching](https://mlsanity.com/paper/2204.00559/) (2022)
- [Image-based Localization using Hourglass Networks](https://mlsanity.com/paper/1703.07971/) (2017)
- [On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation](https://mlsanity.com/paper/2109.00524/) (2021)
- [VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry](https://mlsanity.com/paper/1804.08366/) (2018)
- [Direct-PoseNet: Absolute Pose Regression with Photometric Consistency](https://mlsanity.com/paper/2104.04073/) (2021)
- [Deep Auxiliary Learning for Visual Localization and Odometry](https://mlsanity.com/paper/1803.03642/) (2018)
- [VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalization](https://mlsanity.com/paper/1702.06521/) (2017)
- [Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation](https://mlsanity.com/paper/2012.11002/) (2020)
- [CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization](https://mlsanity.com/paper/2103.10796/) (2021)
- [6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference](https://mlsanity.com/paper/2004.04807/) (2020)
- [Reassessing the Limitations of CNN Methods for Camera Pose Regression](https://mlsanity.com/paper/2108.07260/) (2021)
- [A Probabilistic Framework for Visual Localization in Ambiguous Scenes](https://mlsanity.com/paper/2301.02086/) (2023)

## Built on by (most cited first, 16 of 16)

- [GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2408.11085/) (2024)
- [Learning Neural Volumetric Pose Features for Camera Localization](https://mlsanity.com/paper/2403.12800/) (2024)
- [HGSLoc: 3DGS-based Heuristic Camera Pose Refinement](https://mlsanity.com/paper/2409.10925/) (2024)
- [LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images](https://mlsanity.com/paper/2410.11505/) (2024)
- [GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations](https://mlsanity.com/paper/2508.18242/) (2025)
- [LiteVLoc: Map-Lite Visual Localization for Image Goal Navigation](https://mlsanity.com/paper/2410.04419/) (2024)
- [Adversarial Exploitation of Data Diversity Improves Visual Localization](https://mlsanity.com/paper/2412.00138/) (2024)
- [AIR-HLoc: Adaptive Retrieved Images Selection for Efficient Visual Localisation](https://mlsanity.com/paper/2403.18281/) (2024)
- [Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2508.17876/) (2025)
- [GRLoc: Geometric Representation Regression for Visual Localization](https://mlsanity.com/paper/2511.13864/) (2025)
- [Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty](https://mlsanity.com/paper/2603.16538/) (2026)
- [Quantifying Epistemic Uncertainty in Absolute Pose Regression](https://mlsanity.com/paper/2504.07260/) (2025)
- [SGLoc: Semantic Localization System for Camera Pose Estimation from 3D Gaussian Splatting Representation](https://mlsanity.com/paper/2507.12027/) (2025)
- [L3:Scene-agnostic Visual Localization in the Wild](https://mlsanity.com/paper/2603.07937/) (2026)
- [IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1](https://mlsanity.com/paper/2603.19625/) (2026)
- [Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting](https://mlsanity.com/paper/2603.29185/) (2026)

## Abstract (arXiv)

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4% and 15.2% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs.