# DFNet: Enhance Absolute Pose Regression with Direct Feature Matching

arXiv: https://arxiv.org/abs/2204.00559 · HTML: https://mlsanity.com/paper/2204.00559/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 1 Apr 2022.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [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)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [INeRF: Inverting Neural Radiance Fields for Pose Estimation](https://mlsanity.com/paper/2012.05877/) (2020)
- [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)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [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)
- [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)
- [Dual-Resolution Correspondence Networks](https://mlsanity.com/paper/2006.08844/) (2020)
- [Image-based Localization using Hourglass Networks](https://mlsanity.com/paper/1703.07971/) (2017)
- [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)
- [CoordiNet: uncertainty-aware pose regressor for reliable vehicle localization](https://mlsanity.com/paper/2103.10796/) (2021)
- [Reassessing the Limitations of CNN Methods for Camera Pose Regression](https://mlsanity.com/paper/2108.07260/) (2021)
- [Paying Attention to Activation Maps in Camera Pose Regression](https://mlsanity.com/paper/2103.11477/) (2021)

## Built on by (most cited first, 30 of 82)

- [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)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [Map-Relative Pose Regression for Visual Re-Localization](https://mlsanity.com/paper/2404.09884/) (2024)
- [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)
- [GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting](https://mlsanity.com/paper/2408.11085/) (2024)
- [360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries](https://mlsanity.com/paper/2311.17389/) (2023)
- [NeRF-Loc: Visual Localization with Conditional Neural Radiance Field](https://mlsanity.com/paper/2304.07979/) (2023)
- [HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer](https://mlsanity.com/paper/2305.03595/) (2023)
- [When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation](https://mlsanity.com/paper/2206.13850/) (2022)
- [PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields](https://mlsanity.com/paper/2312.10649/) (2023)
- [The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement](https://mlsanity.com/paper/2404.10438/) (2024)
- [LATITUDE: Robotic Global Localization with Truncated Dynamic Low-pass Filter in City-scale NeRF](https://mlsanity.com/paper/2209.08498/) (2022)
- [HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisation](https://mlsanity.com/paper/2402.14371/) (2024)
- [NeRFs in Robotics: A Survey](https://mlsanity.com/paper/2405.01333/) (2024)
- [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)
- [Towards Foundation Models for 3D Vision: How Close Are We?](https://mlsanity.com/paper/2410.10799/) (2024)
- [Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localization](https://mlsanity.com/paper/2310.06984/) (2023)
- [Learning Neural Volumetric Pose Features for Camera Localization](https://mlsanity.com/paper/2403.12800/) (2024)
- [Few-shot Novel View Synthesis using Depth Aware 3D Gaussian Splatting](https://mlsanity.com/paper/2410.11080/) (2024)
- [LightLoc: Learning Outdoor LiDAR Localization at Light Speed](https://mlsanity.com/paper/2503.17814/) (2025)
- [Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localization](https://mlsanity.com/paper/2507.23569/) (2025)
- [A Guide to Structureless Visual Localization](https://mlsanity.com/paper/2504.17636/) (2025)
- [ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training](https://mlsanity.com/paper/2510.11605/) (2025)
- [Improving Feature-based Visual Localization by Geometry-Aided Matching](https://mlsanity.com/paper/2211.08712/) (2022)
- [HGSLoc: 3DGS-based Heuristic Camera Pose Refinement](https://mlsanity.com/paper/2409.10925/) (2024)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [RDPN6D: Residual-based Dense Point-wise Network for 6Dof Object Pose Estimation Based on RGB-D Images](https://mlsanity.com/paper/2405.08483/) (2024)

## Abstract (arXiv)

We introduce a camera relocalization pipeline that combines absolute pose regression (APR) and direct feature matching. By incorporating exposure-adaptive novel view synthesis, our method successfully addresses photometric distortions in outdoor environments that existing photometric-based methods fail to handle. With domain-invariant feature matching, our solution improves pose regression accuracy using semi-supervised learning on unlabeled data. In particular, the pipeline consists of two components: Novel View Synthesizer and DFNet. The former synthesizes novel views compensating for changes in exposure and the latter regresses camera poses and extracts robust features that close the domain gap between real images and synthetic ones. Furthermore, we introduce an online synthetic data generation scheme. We show that these approaches effectively enhance camera pose estimation both in indoor and outdoor scenes. Hence, our method achieves a state-of-the-art accuracy by outperforming existing single-image APR methods by as much as 56%, comparable to 3D structure-based methods.