mlsanityData to 7 Oct 2026

Image-based Localization using Hourglass Networks

arXiv 1703.07971 ↗First posted 23 Mar 2017cs.CVcited by 63

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGB-image. The architecture has a hourglass shape consisting of a chain of convolution and up-convolution layers followed by a regression part. The up-convolution layers are introduced to preserve the fine-grained information of the input image. Following the common practice, we train our model in end-to-end manner utilizing transfer learning from large scale classification data. The experiments demonstrate the performance of the approach on data exhibiting different lighting conditions, reflections, and motion blur. The results indicate a clear improvement over the previous state-of-the-art even when compared to methods that utilize sequence of test frames instead of a single frame.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 13; 2023: 15; 2024: 15; 2025: 6; 2026: 1.

63 papers.

Sort:

By area:

  1. 2021GNeRF: GAN-based Neural Radiance Field without Posed Cameracited by 153
  2. 2021Learning Multi-Scene Absolute Pose Regression with Transformerscited by 108
  3. 2022DFNet: Enhance Absolute Pose Regression with Direct Feature Matchingcited by 82
  4. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  5. 2023Independent Component Alignment for Multi-Task Learningcited by 69
  6. 2021Direct-PoseNet: Absolute Pose Regression with Photometric Consistencycited by 61
  7. 2024Map-Relative Pose Regression for Visual Re-Localizationcited by 42
  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. 2021CoordiNet: uncertainty-aware pose regressor for reliable vehicle localizationcited by 34
  11. 2022Camera Pose Auto-Encoders for Improving Pose Regressioncited by 28
  12. 2023360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queriescited by 28
38 more
  1. 2023HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformercited by 26
  2. 2021Continual Learning for Image-Based Camera Localizationcited by 18
  3. 2022Leveraging Equivariant Features for Absolute Pose Regressioncited by 17
  4. 2024HR-APR: APR-agnostic Framework with Uncertainty Estimation and Hierarchical Refinement for Camera Relocalisationcited by 16
  5. 2021Wide-Baseline Multi-Camera Calibration using Person Re-Identificationcited by 15
  6. 2023Deep Learning for Visual Localization and Mapping: A Surveycited by 14
  7. 2024Learning Neural Volumetric Pose Features for Camera Localizationcited by 11
  8. 2021Paying Attention to Activation Maps in Camera Pose Regressioncited by 10
  9. 2023EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localizationcited by 8
  10. 2022A Critical Analysis of Image-based Camera Pose Estimation Techniquescited by 7
  11. 20213D-Aware Ellipse Prediction for Object-Based Camera Pose Estimationcited by 6
  12. 2022Semantic Segmentation using Neural Ordinary Differential Equationscited by 6
  13. 2021Pose-GNN : Camera Pose Estimation System Using Graph Neural Networkscited by 4
  14. 2022Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Predictioncited by 4
  15. 2023Learning to Localize in Unseen Scenes with Relative Pose Regressorscited by 3
  16. 2021TransCamP: Graph Transformer for 6-DoF Camera Pose Estimationcited by 2
  17. 2022Objects Matter: Learning Object Relation Graph for Robust Camera Relocalizationcited by 2
  18. 2022Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regressioncited by 2
  19. 2023FusionLoc: Camera-2D LiDAR Fusion Using Multi-Head Self-Attention for End-to-End Serving Robot Relocalizationcited by 2
  20. 2023CoPR: Towards Accurate Visual Localization With Continuous Place-descriptor Regressioncited by 2
  21. 2024Conditional Variational Autoencoders for Probabilistic Pose Regressioncited by 2
  22. 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired Peoplecited by 2
  23. 2022Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimationcited by 1
  24. 2022A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objectivecited by 1
  25. 2023HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Datasetcited by 1
  26. 2023Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Camerascited by 1
  27. 2024MobileARLoc: On-device Robust Absolute Localisation for Pervasive Markerless Mobile ARcited by 1
  28. 2024On the Effect of Image Resolution on Semantic Segmentationcited by 1
  29. 2024Camera Relocalization in Shadow-free Neural Radiance Fieldscited by 1
  30. 2024Enhancing Scene Coordinate Regression with Efficient Keypoint Detection and Sequential Informationcited by 1
  31. 2025MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalizationcited by 1
  32. 2021Deep Weakly Supervised Positioningcited by 0
  33. 2021Deep auxiliary learning for visual localization using colorization taskcited by 0
  34. 2022Deep Camera Pose Regression Using Pseudo-LiDARcited by 0
  35. 2022S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalizationcited by 0
  36. 2022Graph Attention Network for Camera Relocalization on Dynamic Scenescited by 0
  37. 2023Synfeal: A Data-Driven Simulator for End-to-End Camera Localizationcited by 0
  38. 2023Robust Localization with Visual-Inertial Odometry Constraints for Markerless Mobile ARcited by 0

50 most cited of 63 All 63 (JSON)