mlsanityData to 7 Oct 2026

R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization

arXiv 2501.01421 ↗First posted 2 Jan 2025cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Learning-based visual localization methods that use scene coordinate regression (SCR) offer the advantage of smaller map sizes. However, on datasets with complex illumination changes or image-level ambiguities, it remains a less robust alternative to feature matching methods. This work aims to close the gap. We introduce a covisibility graph-based global encoding learning and data augmentation strategy, along with a depth-adjusted reprojection loss to facilitate implicit triangulation. Additionally, we revisit the network architecture and local feature extraction module. Our method achieves state-of-the-art on challenging large-scale datasets without relying on network ensembles or 3D supervision. On Aachen Day-Night, we are 10× more accurate than previous SCR methods with similar map sizes and require at least 5× smaller map sizes than any other SCR method while still delivering superior accuracy. Code is available at: https://github.com/cvg/scrstudio .

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 55 of its 86 references that are in the map. First posted on arXiv 2 Jan 2025.

Builds on

55 of 86 references.

References · 55

  1. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  7. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  9. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  10. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
  11. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
38 more
  1. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  2. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  3. 2018Model compression via distillation and quantizationcited by 287
  4. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  5. 2017A General and Adaptive Robust Loss Functioncited by 236
  6. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  7. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  8. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  9. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  10. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  11. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 160
  12. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  13. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  14. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  15. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  16. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  17. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  18. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  19. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  20. 2022MeshLoc: Mesh-Based Visual Localizationcited by 62
  21. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  22. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  23. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  24. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  25. 2018Hybrid Scene Compression for Visual Localizationcited by 40
  26. 2017On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisationcited by 38
  27. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  28. 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
  29. 2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
  30. 2018Real-Time RGB-D Camera Pose Estimation in Novel Scenes using a Relocalisation Cascadecited by 35
  31. 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
  32. 2021Large-scale Localization Datasets in Crowded Indoor Spacescited by 28
  33. 2022NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localizationcited by 26
  34. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  35. 2023Some Fundamental Aspects about Lipschitz Continuity of Neural Networkscited by 25
  36. 2020Learning to Localize in New Environments from Synthetic Training Datacited by 21
  37. 2019Cascaded Parallel Filtering for Memory-Efficient Image-Based Localizationcited by 17
  38. 2023DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matchingcited by 17

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 10.

16 papers.

Sort:

By area:

  1. 2025Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Datasetcited by 8
  2. 2025GRLoc: Geometric Representation Regression for Visual Localizationcited by 1
  3. 2026ImLoc: Revisiting Visual Localization with Image-based Representationcited by 1
  4. 2026SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddingscited by 1
  5. 2025MACE: Mixture-of-Experts Accelerated Coordinate Encoding for Large-Scale Scene Localization and Renderingcited by 0
  6. 2025Visible Structure Retrieval for Lightweight Image-Based Relocalisationcited by 0
  7. 2025ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAMcited by 0
  8. 2025Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptorscited by 0
  9. 2026L3:Scene-agnostic Visual Localization in the Wildcited by 0
  10. 2026PlanaReLoc: Camera Relocalization in 3D Planar Primitives via Region-Based Structure Matchingcited by 0
  11. 2026LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarioscited by 0
  12. 2026Continual Hand-Eye Calibration for Open-world Robotic Manipulationcited by 0
4 more
  1. 2026LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localizationcited by 0
  2. 2026AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labelscited by 0
  3. 2026VideoReloc: Long-Term Indoor Video Relocalization against a Kilobyte-Scale Semantic Scene Graphcited by 0
  4. 2026NaCR: Visual Localization via NeRF-aided Camera Ray Regressioncited by 0