# CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation

arXiv: https://arxiv.org/abs/2303.04869 · HTML: https://mlsanity.com/paper/2303.04869/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 8 Mar 2023.

## Builds on (most cited first, 30 of 39)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [Block-NeRF: Scalable Large Scene Neural View Synthesis](https://mlsanity.com/paper/2202.05263/) (2022)
- [RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs](https://mlsanity.com/paper/2112.00724/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields](https://mlsanity.com/paper/2210.13641/) (2022)
- [Understanding the Limitations of CNN-based Absolute Camera Pose Regression](https://mlsanity.com/paper/1903.07504/) (2019)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Vision-Only Robot Navigation in a Neural Radiance World](https://mlsanity.com/paper/2110.00168/) (2021)
- [SOSNet: Second Order Similarity Regularization for Local Descriptor Learning](https://mlsanity.com/paper/1904.05019/) (2019)
- [LENS: Localization enhanced by NeRF synthesis](https://mlsanity.com/paper/2110.06558/) (2021)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Learning Feature Descriptors using Camera Pose Supervision](https://mlsanity.com/paper/2004.13324/) (2020)
- [NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields](https://mlsanity.com/paper/2203.01913/) (2022)
- [Universal Correspondence Network](https://mlsanity.com/paper/1606.03558/) (2016)
- [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)
- [MeshLoc: Mesh-Based Visual Localization](https://mlsanity.com/paper/2207.10762/) (2022)
- [Direct-PoseNet: Absolute Pose Regression with Photometric Consistency](https://mlsanity.com/paper/2104.04073/) (2021)
- [Parallel Inversion of Neural Radiance Fields for Robust Pose Estimation](https://mlsanity.com/paper/2210.10108/) (2022)

## Built on by (most cited first, 30 of 45)

- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [The NeRFect Match: Exploring NeRF Features for Visual Localization](https://mlsanity.com/paper/2403.09577/) (2024)
- [GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2408.11085/) (2024)
- [6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model](https://mlsanity.com/paper/2407.15484/) (2024)
- [The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement](https://mlsanity.com/paper/2404.10438/) (2024)
- [Deep Learning for Camera Calibration and Beyond: A Survey](https://mlsanity.com/paper/2303.10559/) (2023)
- [GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization](https://mlsanity.com/paper/2409.16502/) (2024)
- [From Sparse to Dense: Camera Relocalization with Scene-Specific Detector from Feature Gaussian Splatting](https://mlsanity.com/paper/2503.19358/) (2025)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [SOAC: Spatio-Temporal Overlap-Aware Multi-Sensor Calibration using Neural Radiance Fields](https://mlsanity.com/paper/2311.15803/) (2023)
- [3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration](https://mlsanity.com/paper/2403.11577/) (2024)
- [Learning Neural Volumetric Pose Features for Camera Localization](https://mlsanity.com/paper/2403.12800/) (2024)
- [Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization](https://mlsanity.com/paper/2507.23569/) (2025)
- [MeshVPR: Citywide Visual Place Recognition Using 3D Meshes](https://mlsanity.com/paper/2406.02776/) (2024)
- [IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model](https://mlsanity.com/paper/2403.12682/) (2024)
- [Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement](https://mlsanity.com/paper/2406.08463/) (2024)
- [SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimization](https://mlsanity.com/paper/2407.12667/) (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)
- [PEnG: Pose-Enhanced Geo-Localisation](https://mlsanity.com/paper/2411.15742/) (2024)
- [SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splatting](https://mlsanity.com/paper/2503.05174/) (2025)
- [Can we make NeRF-based visual localization privacy-preserving?](https://mlsanity.com/paper/2508.18971/) (2025)
- [ConDo: Continual Domain Expansion for Absolute Pose Regression](https://mlsanity.com/paper/2412.13452/) (2024)
- [FaVoR: Features via Voxel Rendering for Camera Relocalization](https://mlsanity.com/paper/2409.07571/) (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)
- [ImLoc: Revisiting Visual Localization with Image-based Representation](https://mlsanity.com/paper/2601.04185/) (2026)
- [Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty](https://mlsanity.com/paper/2603.16538/) (2026)
- [PRAM: Place Recognition Anywhere Model for Efficient Visual Localization](https://mlsanity.com/paper/2404.07785/) (2024)

## Abstract (arXiv)

Beyond novel view synthesis, Neural Radiance Fields are useful for applications that interact with the real world. In this paper, we use them as an implicit map of a given scene and propose a camera relocalization algorithm tailored for this representation. The proposed method enables to compute in real-time the precise position of a device using a single RGB camera, during its navigation. In contrast with previous work, we do not rely on pose regression or photometric alignment but rather use dense local features obtained through volumetric rendering which are specialized on the scene with a self-supervised objective. As a result, our algorithm is more accurate than competitors, able to operate in dynamic outdoor environments with changing lightning conditions and can be readily integrated in any volumetric neural renderer.