mlsanityData to 14 Oct 2026

Lazy Visual Localization via Motion Averaging

arXiv 2307.09981 ↗First posted 19 Jul 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Visual (re)localization is critical for various applications in computer vision and robotics. Its goal is to estimate the 6 degrees of freedom (DoF) camera pose for each query image, based on a set of posed database images. Currently, all leading solutions are structure-based that either explicitly construct 3D metric maps from the database with structure-from-motion, or implicitly encode the 3D information with scene coordinate regression models. On the contrary, visual localization without reconstructing the scene in 3D offers clear benefits. It makes deployment more convenient by reducing database pre-processing time, releasing storage requirements, and remaining unaffected by imperfect reconstruction, etc. In this technical report, we demonstrate that it is possible to achieve high localization accuracy without reconstructing the scene from the database. The key to achieving this owes to a tailored motion averaging over database-query pairs. Experiments show that our visual localization proposal, LazyLoc, achieves comparable performance against state-of-the-art structure-based methods. Furthermore, we showcase the versatility of LazyLoc, which can be easily extended to handle complex configurations such as multi-query co-localization and camera rigs.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 84 references that are in the map. First posted on arXiv 19 Jul 2023.

Builds on

39 of 84 references.

References · 39

  1. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  4. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  5. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  6. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  7. 2020Learning to Explore using Active Neural SLAMcited by 316
  8. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  9. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  10. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  11. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 185
  12. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
27 more
  1. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  2. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  3. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 134
  4. 2016End-to-end Learning of Deep Visual Representations for Image Retrievalcited by 122
  5. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  6. 2020Self-supervising Fine-grained Region Similarities for Large-scale Image Localizationcited by 110
  7. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  8. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  9. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  10. 2022MeshLoc: Mesh-Based Visual Localizationcited by 62
  11. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  12. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  13. 2020KFNet: Learning Temporal Camera Relocalization using Kalman Filteringcited by 43
  14. 2014Robust Camera Location Estimation by Convex Programmingcited by 41
  15. 2017On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisationcited by 38
  16. 2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
  17. 2018Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascadecited by 35
  18. 2020HoloLens 2 Research Mode as a Tool for Computer Vision Researchcited by 34
  19. 2020Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenescited by 31
  20. 2021VS-Net: Voting with Segmentation for Visual Localizationcited by 29
  21. 2019Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisationcited by 28
  22. 2021Learning Camera Localization via Dense Scene Matchingcited by 28
  23. 2019Baseline Desensitizing In Translation Averagingcited by 27
  24. 2020Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environmentscited by 19
  25. 2021CrowdDriven: A New Challenging Dataset for Outdoor Visual Localizationcited by 13
  26. 2021Calibrated and Partially Calibrated Semi-Generalized Homographiescited by 12
  27. 2020Towards Accurate Active Camera Localizationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 1; 2026: 3.

8 papers.

  1. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  2. 2024Learning Neural Volumetric Pose Features for Camera Localizationcited by 11
  3. 2025A Guide to Structureless Visual Localizationcited by 9
  4. 2024Combining Absolute and Semi-Generalized Relative Poses for Visual Localizationcited by 4
  5. 2024LiteVLoc: Map-Lite Visual Localization for Image Goal Navigationcited by 4
  6. 2026ImLoc: Revisiting Visual Localization with Image-based Representationcited by 1
  7. 2026Privacy-Preserving Structureless Visual Localization via Image Obfuscationcited by 0
  8. 2026Accuracy potential of visual localization exploiting high-end street-level imagerycited by 0