mlsanityData to 7 Oct 2026

AtLoc: Attention Guided Camera Localization

arXiv 1909.03557 ↗First posted 8 Sep 2019cs.CVcited by 92

Not on the map. Why?

Abstract (arXiv)

Deep learning has achieved impressive results in camera localization, but current single-image techniques typically suffer from a lack of robustness, leading to large outliers. To some extent, this has been tackled by sequential (multi-images) or geometry constraint approaches, which can learn to reject dynamic objects and illumination conditions to achieve better performance. In this work, we show that attention can be used to force the network to focus on more geometrically robust objects and features, achieving state-of-the-art performance in common benchmark, even if using only a single image as input. Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. The source code is avaliable at https://github.com/BingCS/AtLoc.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 19; 2023: 16; 2024: 22; 2025: 20; 2026: 2.

92 papers.

Sort:

By area:

  1. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  2. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  3. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  4. 2023SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environmentscited by 47
  5. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  6. 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
  7. 2022HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDARcited by 38
  8. 2021Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervisioncited by 37
  9. 2023Neural Refinement for Absolute Pose Regression with Feature Synthesiscited by 37
  10. 2022Visual Localization via Few-Shot Scene Region Classificationcited by 36
  11. 2021CoordiNet: uncertainty-aware pose regressor for reliable vehicle localizationcited by 34
  12. 2024GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splattingcited by 31
38 more
  1. 2021VS-Net: Voting with Segmentation for Visual Localizationcited by 29
  2. 2021CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Datacited by 28
  3. 2022Camera Pose Auto-Encoders for Improving Pose Regressioncited by 28
  4. 2025UAVScenes: A Multi-Modal Dataset for UAVscited by 26
  5. 2023HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusioncited by 24
  6. 2021Reassessing the Limitations of CNN Methods for Camera Pose Regressioncited by 19
  7. 2022RobustLoc: Robust Camera Pose Regression in Challenging Driving Environmentscited by 18
  8. 2022Leveraging Equivariant Features for Absolute Pose Regressioncited by 17
  9. 2024HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisationcited by 16
  10. 2024GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localizationcited by 15
  11. 2022SC-wLS: Towards Interpretable Feed-forward Camera Re-localizationcited by 14
  12. 2023SACReg: Scene-Agnostic Coordinate Regression for Visual Localizationcited by 14
  13. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  14. 2021Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networkscited by 12
  15. 2023Coarse-to-Fine Multi-Scene Pose Regression with Transformerscited by 11
  16. 2021Paying Attention to Activation Maps in Camera Pose Regressioncited by 10
  17. 2025LightLoc: Learning Outdoor LiDAR Localization at Light Speedcited by 10
  18. 2025Gaussian Splatting Feature Fields for Privacy-Preserving Visual Localizationcited by 10
  19. 2024HGSLoc: 3DGS-based Heuristic Camera Pose Refinementcited by 8
  20. 2025ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Trainingcited by 8
  21. 2022A Critical Analysis of Image-based Camera Pose Estimation Techniquescited by 7
  22. 2022EMA-VIO: Deep Visual-Inertial Odometry with External Memory Attentioncited by 6
  23. 2023Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometrycited by 6
  24. 2021RadarLoc: Learning to Relocalize in FMCW Radarcited by 5
  25. 2024Self-supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinementcited by 5
  26. 2024HiSC4D: Human-centered interaction and 4D Scene Capture in Large-scale Space Using Wearable IMUs and LiDARcited by 5
  27. 2022PixSelect: Less but Reliable Pixels for Accurate and Efficient Localizationcited by 4
  28. 2024Improved Scene Landmark Detection for Camera Localizationcited by 4
  29. 2024Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Informationcited by 4
  30. 2024Adversarial Exploitation of Data Diversity Improves Visual Localizationcited by 4
  31. 2025Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelinescited by 4
  32. 2022Fusing Convolutional Neural Network and Geometric Constraint for Image-based Indoor Localizationcited by 3
  33. 2022ImPosing: Implicit Pose Encoding for Efficient Visual Localizationcited by 3
  34. 2022Fast and Lightweight Scene Regressor for Camera Relocalizationcited by 3
  35. 2023Learning to Localize in Unseen Scenes with Relative Pose Regressorscited by 3
  36. 2024EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalizationcited by 3
  37. 2024FlashMix: Fast Map-Free LiDAR Localization via Feature Mixing and Contrastive-Constrained Accelerated Trainingcited by 3
  38. 2022Objects Matter: Learning Object Relation Graph for Robust Camera Relocalizationcited by 2

50 most cited of 92 All 92 (JSON)