mlsanityData to 7 Oct 2026

A Critical Analysis of Image-based Camera Pose Estimation Techniques

arXiv 2201.05816 ↗First posted 15 Jan 2022cs.CV cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR). In this survey, we first introduce specific application areas and the evaluation metrics for camera localization pose according to different sub-tasks (learning-based 2D-2D task, feature-based 2D-3D task, and 3D-3D task). Then, we review common methods for structure-based camera pose estimation approaches, absolute pose regression and relative pose regression approaches by critically modelling the methods to inspire further improvements in their algorithms such as loss functions, neural network structures. Furthermore, we summarise what are the popular datasets used for camera localization and compare the quantitative and qualitative results of these methods with detailed performance metrics. Finally, we discuss future research possibilities and applications.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 65 of its 128 references that are in the map. First posted on arXiv 15 Jan 2022.

Builds on

65 of 128 references.

References · 65

  1. 2014Going Deeper with Convolutionscited by 4,231
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  3. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  4. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  5. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  6. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  7. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 333
  8. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  9. 2014CNN Features off-the-shelf: an Astounding Baseline for Recognitioncited by 316
  10. 2016LIFT: Learned Invariant Feature Transformcited by 305
  11. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  12. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
38 more
  1. 2017Geometric Loss Functions for Camera Pose Regression with Deep Learningcited by 224
  2. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  3. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 188
  4. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  5. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  6. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  7. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  8. 2017Learning Less is More - 6D Camera Localization via 3D Surface Regressioncited by 146
  9. 2016Image-based localization using LSTMs for structured feature correlationcited by 136
  10. 2015Modelling Uncertainty in Deep Learning for Camera Relocalizationcited by 133
  11. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  12. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  13. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  14. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  15. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  16. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  17. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  18. 2019Hierarchical Scene Coordinate Classification and Regression for Visual Localizationcited by 93
  19. 2019AtLoc: Attention Guided Camera Localizationcited by 92
  20. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  21. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  22. 2019Expert Sample Consensus Applied to Camera Re-Localizationcited by 70
  23. 2018DGC-Net: Dense Geometric Correspondence Networkcited by 67
  24. 2017Image-based Localization using Hourglass Networkscited by 63
  25. 2018VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometrycited by 61
  26. 2019To Learn or Not to Learn: Visual Localization from Essential Matricescited by 61
  27. 2018Deep Auxiliary Learning for Visual Localization and Odometrycited by 59
  28. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  29. 2017VidLoc: A Deep Spatio-Temporal Model for 6-DoF Video-Clip Relocalizationcited by 58
  30. 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
  31. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  32. 2018Detect-to-Retrieve: Efficient Regional Aggregation for Image Searchcited by 39
  33. 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
  34. 2020A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligencecited by 35
  35. 2020D2D: Keypoint Extraction with Describe to Detect Approachcited by 34
  36. 2016Learning Covariant Feature Detectorscited by 25
  37. 2019Introduction to Camera Pose Estimation with Deep Learningcited by 25
  38. 2019Local Supports Global: Deep Camera Relocalization with Sequence Enhancementcited by 25

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenoncited by 16
  2. 2023Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environmentscited by 5
  3. 2023HyperPose: Hypernetwork-Infused Camera Pose Localization and an Extended Cambridge Landmarks Datasetcited by 1
  4. 2024MambaLoc: Efficient Camera Localisation via State Space Modelcited by 0
  5. 2024Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graphcited by 0
  6. 2025Stable Single-Pixel Contrastive Learning for Semantic and Geometric Taskscited by 0
  7. 2026Automatic dental superimposition of 3D intraorals and 2D photographs for human identificationcited by 0