mlsanityData to 7 Oct 2026

Self-Supervised Equivariant Learning for Oriented Keypoint Detection

arXiv 2204.08613 ↗First posted 19 Apr 2022cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

Detecting robust keypoints from an image is an integral part of many computer vision problems, and the characteristic orientation and scale of keypoints play an important role for keypoint description and matching. Existing learning-based methods for keypoint detection rely on standard translation-equivariant CNNs but often fail to detect reliable keypoints against geometric variations. To learn to detect robust oriented keypoints, we introduce a self-supervised learning framework using rotation-equivariant CNNs. We propose a dense orientation alignment loss by an image pair generated by synthetic transformations for training a histogram-based orientation map. Our method outperforms the previous methods on an image matching benchmark and a camera pose estimation benchmark.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 48 of its 79 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

48 of 79 references.

References · 48

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  4. 2015Spatial Transformer Networkscited by 1,423
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  6. 2016Group Equivariant Convolutional Networkscited by 1,154
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  8. 2019General E(2)-Equivariant Steerable CNNscited by 441
  9. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  10. 2020DISK: Learning local features with policy gradientcited by 310
  11. 2016LIFT: Learned Invariant Feature Transformcited by 305
  12. 2016Steerable CNNscited by 298
36 more
  1. 2016Harmonic Networks: Deep Translation and Rotation Equivariancecited by 293
  2. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  3. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  4. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  5. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  6. 2018A General Theory of Equivariant CNNs on Homogeneous Spacescited by 223
  7. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  8. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  9. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 193
  10. 2017Learning to Find Good Correspondencescited by 176
  11. 2018Neighbourhood Consensus Networkscited by 173
  12. 2018LF-Net: Learning Local Features from Imagescited by 151
  13. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  14. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  15. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  16. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  17. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  18. 2019Scale-Equivariant Steerable Networkscited by 110
  19. 2016Rotation equivariant vector field networkscited by 98
  20. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  21. 2016Universal Correspondence Networkcited by 82
  22. 2017Oriented Response Networkscited by 67
  23. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  24. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  25. 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
  26. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  27. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  28. 2019Large-scale, real-time visual-inertial localization revisitedcited by 45
  29. 2020CoMIR: Contrastive Multimodal Image Representation for Registrationcited by 45
  30. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  31. 2017Toward Geometric Deep SLAMcited by 38
  32. 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
  33. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  34. 2016Learning Covariant Feature Detectorscited by 25
  35. 2019RF-Net: An End-to-End Image Matching Network based on Receptive Fieldcited by 22
  36. 2015Learning to Assign Orientations to Feature Pointscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 5; 2025: 5; 2026: 6.

26 papers.

Sort:

  1. 20246DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Modelcited by 28
  2. 2022Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Workscited by 24
  3. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  4. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
  5. 2022E2PN: Efficient SE(3)-Equivariant Point Networkcited by 17
  6. 2023S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extractioncited by 13
  7. 2024Learning to Make Keypoints Sub-Pixel Accuratecited by 13
  8. 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 12
  9. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  10. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  11. 2024Affine steerers for structured keypoint descriptioncited by 6
  12. 2023NeSS-ST: Detecting Good and Stable Keypoints with a Neural Stability Score and the Shi-Tomasi Detectorcited by 5
14 more
  1. 2023RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopycited by 5
  2. 2024Incorporating Arbitrary Matrix Group Equivariance into KANscited by 4
  3. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  4. 2026Second-order Gaussian directional derivative representations for image high-resolution corner detectioncited by 3
  5. 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
  6. 2025SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splattingcited by 2
  7. 2026Who Handles Orientation? Investigating Invariance in Feature Matchingcited by 1
  8. 2022SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithmscited by 0
  9. 2023Residual Learning for Image Point Descriptorscited by 0
  10. 2025Good Keypoints for the Two-View Geometry Estimation Problemcited by 0
  11. 2025Equivariant symmetry-aware head pose estimation for fetal MRIcited by 0
  12. 2026From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detectioncited by 0
  13. 2026REViT: Roto-reflection Equivariant Convolutional Vision Transformercited by 0
  14. 2026SSMB: Self-Supervised Local Feature Detection under Motion Blurcited by 0