mlsanityData to 14 Oct 2026

GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations

arXiv 2508.18242 ↗First posted 25 Aug 2025cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We accomplish this by robustly matching scene features to image features. Scene features are produced by downsampling and encoding the 3D Gaussians while image features are obtained by encoding image patches. Our algorithm proceeds in three steps, starting with coarse matching, then fine matching, and finally by applying pose refinement for an accurate final estimate. Importantly, our method leverages the explicit 3DGS scene representation for visual localization without requiring modifications, retraining, or additional reference images. We evaluate GSVisLoc on both indoor and outdoor scenes, demonstrating competitive localization performance on standard benchmarks while outperforming existing 3DGS-based baselines. Moreover, our approach generalizes effectively to novel scenes without additional training.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 63 of its 92 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

63 of 92 references.

References · 63

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  9. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  10. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  11. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
38 more
  1. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  2. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  3. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
  4. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  5. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  6. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  7. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  8. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  9. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  10. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  11. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  12. 2022Rethinking Visual Geo-localization for Large-Scale Applicationscited by 163
  13. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  14. 2023Segment Any 3D Gaussianscited by 161
  15. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  16. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  17. 2022MetaFormer Baselines for Visioncited by 132
  18. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 129
  19. 2021LENS: Localization enhanced by NeRF synthesiscited by 117
  20. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  21. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  22. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  23. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  24. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  25. 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
  26. 2021On the Limits of Pseudo Ground Truth in Visual Camera Re-localisationcited by 63
  27. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  28. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  29. 2024GLACE: Global Local Accelerated Coordinate Encodingcited by 48
  30. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  31. 2023CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representationcited by 45
  32. 2018Hybrid Scene Compression for Visual Localizationcited by 40
  33. 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
  34. 2018Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera Systemcited by 34
  35. 2024The NeRFect Match: Exploring NeRF Features for Visual Localizationcited by 32
  36. 2018RPNet: an End-to-End Network for Relative Camera Pose Estimationcited by 31
  37. 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
  38. 2017An Efficient Algebraic Solution to the Perspective-Three-Point Problemcited by 29

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026DRoPS: Dynamic 3D Reconstruction of Pre-Scanned Objectscited by 1
  2. 2026LSGS-Loc: Towards Robust 3DGS-Based Visual Localization for Large-Scale UAV Scenarioscited by 0
  3. 2026Disambiguating 2D-3D Correspondences in Gaussian Splatting-based Feature Fields for Visual Localizationcited by 0
  4. 2026Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimationcited by 0
  5. 2026SG2Loc: Sequential Visual Localization on 3D Scene Graphscited by 0