mlsanityData to 7 Oct 2026

On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation

arXiv 1702.02779 ↗First posted 9 Feb 2017cs.CVcited by 38

Not on the map. Why?

Abstract (arXiv)

Camera relocalisation is an important problem in computer vision, with applications in simultaneous localisation and mapping, virtual/augmented reality and navigation. Common techniques either match the current image against keyframes with known poses coming from a tracker, or establish 2D-to-3D correspondences between keypoints in the current image and points in the scene in order to estimate the camera pose. Recently, regression forests have become a popular alternative to establish such correspondences. They achieve accurate results, but must be trained offline on the target scene, preventing relocalisation in new environments. In this paper, we show how to circumvent this limitation by adapting a pre-trained forest to a new scene on the fly. Our adapted forests achieve relocalisation performance that is on par with that of offline forests, and our approach runs in under 150ms, making it desirable for real-time systems that require online relocalisation.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 9; 2024: 6; 2025: 7; 2026: 2.

38 papers.

Sort:

By area:

  1. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  2. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  3. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
  4. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  5. 2021On the Limits of Pseudo Ground Truth in Visual Camera Re-localisationcited by 63
  6. 2022MeshLoc: Mesh-Based Visual Localizationcited by 62
  7. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  8. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  9. 2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
  10. 2022Camera Pose Auto-Encoders for Improving Pose Regressioncited by 28
  11. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  12. 2023PNeRFLoc: Visual Localization with Point-based Neural Radiance Fieldscited by 22
26 more
  1. 2023Visual Localization using Imperfect 3D Models from the Internetcited by 20
  2. 2021How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Linescited by 19
  3. 2022Satellite Image Based Cross-view Localization for Autonomous Vehiclecited by 19
  4. 2021Continual Learning for Image-Based Camera Localizationcited by 18
  5. 2023FocusTune: Tuning Visual Localization through Focus-Guided Samplingcited by 16
  6. 2025R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localizationcited by 16
  7. 2024GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localizationcited by 15
  8. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  9. 2021CrowdDriven: A New Challenging Dataset for Outdoor Visual Localizationcited by 13
  10. 2023Leveraging Neural Radiance Fields for Uncertainty-Aware Visual Localizationcited by 12
  11. 2023Lazy Visual Localization via Motion Averagingcited by 8
  12. 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Trainingcited by 8
  13. 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinementcited by 5
  14. 2023Predictive World Models from Real-World Partial Observationscited by 4
  15. 2025A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Featurescited by 4
  16. 2022Fast and Lightweight Scene Regressor for Camera Relocalizationcited by 3
  17. 2024Combining Absolute and Semi-Generalized Relative Poses for Visual Localizationcited by 3
  18. 2025Scene Coordinate Reconstruction Priorscited by 2
  19. 2024Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistencycited by 1
  20. 2021Domain Adaptation of Networks for Camera Pose Estimation: Learning Camera Pose Estimation Without Pose Labelscited by 0
  21. 2022Graph Attention Network for Camera Relocalization on Dynamic Scenescited by 0
  22. 2025Improved 3D Point-Line Mapping Regression for Camera Relocalizationcited by 0
  23. 2025Relative Pose Regression with Pose Auto-Encoders: Enhancing Accuracy and Data Efficiency for Retail Applicationscited by 0
  24. 2025Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptorscited by 0
  25. 2026L3:Scene-agnostic Visual Localization in the Wildcited by 0
  26. 2026AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labelscited by 0