# HAL-NeRF: High Accuracy Localization Leveraging Neural Radiance Fields

arXiv: https://arxiv.org/abs/2504.08901 · HTML: https://mlsanity.com/paper/2504.08901/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 11 Apr 2025.

## Builds on (most cited first, 22 of 22)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [Geometric Loss Functions for Camera Pose Regression with Deep Learning](https://mlsanity.com/paper/1704.00390/) (2017)
- [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)
- [DFNet: Enhance Absolute Pose Regression with Direct Feature Matching](https://mlsanity.com/paper/2204.00559/) (2022)
- [Loc-NeRF: Monte Carlo Localization using Neural Radiance Fields](https://mlsanity.com/paper/2209.09050/) (2022)
- [On the Limits of Pseudo Ground Truth in Visual Camera Re-localisation](https://mlsanity.com/paper/2109.00524/) (2021)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [Neural Refinement for Absolute Pose Regression with Feature Synthesis](https://mlsanity.com/paper/2303.10087/) (2023)
- [The NeRFect Match: Exploring NeRF Features for Visual Localization](https://mlsanity.com/paper/2403.09577/) (2024)
- [Camera Pose Auto-Encoders for Improving Pose Regression](https://mlsanity.com/paper/2207.05530/) (2022)
- [NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization](https://mlsanity.com/paper/2211.11177/) (2022)
- [LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF](https://mlsanity.com/paper/2209.08498/) (2022)
- [Learning Neural Volumetric Pose Features for Camera Localization](https://mlsanity.com/paper/2403.12800/) (2024)
- [Paying Attention to Activation Maps in Camera Pose Regression](https://mlsanity.com/paper/2103.11477/) (2021)

## Abstract (arXiv)

Precise camera localization is a critical task in XR applications and robotics. Using only the camera captures as input to a system is an inexpensive option that enables localization in large indoor and outdoor environments, but it presents challenges in achieving high accuracy. Specifically, camera relocalization methods, such as Absolute Pose Regression (APR), can localize cameras with a median translation error of more than 0.5m in outdoor scenes. This paper presents HAL-NeRF, a high-accuracy localization method that combines a CNN pose regressor with a refinement module based on a Monte Carlo particle filter. The Nerfacto model, an implementation of Neural Radiance Fields (NeRFs), is used to augment the data for training the pose regressor and to measure photometric loss in the particle filter refinement module. HAL-NeRF leverages Nerfacto's ability to synthesize high-quality novel views, significantly improving the performance of the localization pipeline. HAL-NeRF achieves state-of-the-art results that are conventionally measured as the average of the median per scene errors. The translation error was 0.025m and the rotation error was 0.59 degrees and 0.04m and 0.58 degrees on the 7-Scenes dataset and Cambridge Landmarks datasets respectively, with the trade-off of increased computational time. This work highlights the potential of combining APR with NeRF-based refinement techniques to advance monocular camera relocalization accuracy.