# Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis

arXiv: https://arxiv.org/abs/2005.05179 · HTML: https://mlsanity.com/paper/2005.05179/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2020.

## Built on by (most cited first, 10 of 10)

- [ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching](https://mlsanity.com/paper/2204.11700/) (2022)
- [Large-scale Localization Datasets in Crowded Indoor Spaces](https://mlsanity.com/paper/2105.08941/) (2021)
- [A Guide to Structureless Visual Localization](https://mlsanity.com/paper/2504.17636/) (2025)
- [Retrieval and Localization with Observation Constraints](https://mlsanity.com/paper/2108.08516/) (2021)
- [MD-Net: Multi-Detector for Local Feature Extraction](https://mlsanity.com/paper/2208.05350/) (2022)
- [Combining Absolute and Semi-Generalized Relative Poses for Visual Localization](https://mlsanity.com/paper/2409.14269/) (2024)
- [RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments](https://mlsanity.com/paper/2207.12579/) (2022)
- [SGL: Structure Guidance Learning for Camera Localization](https://mlsanity.com/paper/2304.05571/) (2023)
- [Privacy-Preserving Structureless Visual Localization via Image Obfuscation](https://mlsanity.com/paper/2604.12068/) (2026)
- [RIPE++: Reinforced Keypoint Learning from Positive Pairs Only](https://mlsanity.com/paper/2608.19693/) (2026)

## Abstract (arXiv)

Visual Localization is one of the key enabling technologies for autonomous driving and augmented reality. High quality datasets with accurate 6 Degree-of-Freedom (DoF) reference poses are the foundation for benchmarking and improving existing methods. Traditionally, reference poses have been obtained via Structure-from-Motion (SfM). However, SfM itself relies on local features which are prone to fail when images were taken under different conditions, e.g., day/ night changes. At the same time, manually annotating feature correspondences is not scalable and potentially inaccurate. In this work, we propose a semi-automated approach to generate reference poses based on feature matching between renderings of a 3D model and real images via learned features. Given an initial pose estimate, our approach iteratively refines the pose based on feature matches against a rendering of the model from the current pose estimate. We significantly improve the nighttime reference poses of the popular Aachen Day-Night dataset, showing that state-of-the-art visual localization methods perform better (up to 47%) than predicted by the original reference poses. We extend the dataset with new nighttime test images, provide uncertainty estimates for our new reference poses, and introduce a new evaluation criterion. We will make our reference poses and our framework publicly available upon publication.