mlsanityData to 7 Oct 2026

Affine steerers for structured keypoint description

arXiv 2408.14186 ↗First posted 26 Aug 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane. The main idea is to use the representation theory of GL(2) to generalize the recently introduced concept of steerers from rotations to affine transformations. Affine steerers give high control over how keypoint descriptions transform under image transformations. We demonstrate the potential of using this control for image matching. Finally, we propose a way to finetune keypoint descriptors with a set of steerers on upright images and obtain state-of-the-art results on several standard benchmarks. Code will be published at github.com/georg-bn/affine-steerers.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 68 of its 91 references that are in the map. First posted on arXiv 26 Aug 2024.

Builds on

68 of 91 references.

References · 68

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  9. 2016Group Equivariant Convolutional Networkscited by 1,154
  10. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
38 more
  1. 2019General E(2)-Equivariant Steerable CNNscited by 441
  2. 2020DISK: Learning local features with policy gradientcited by 310
  3. 2016LIFT: Learned Invariant Feature Transformcited by 305
  4. 2023RoMa: Robust Dense Feature Matchingcited by 296
  5. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  6. 2014Understanding image representations by measuring their equivariance and equivalencecited by 240
  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. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  10. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  11. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  12. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  13. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 120
  14. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  15. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  16. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  17. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  18. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  19. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  20. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  21. 2024Learning and Leveraging World Models in Visual Representation Learningcited by 71
  22. 2022ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matchingcited by 62
  23. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  24. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  25. 2022Learning Symmetric Embeddings for Equivariant World Modelscited by 54
  26. 2023SiLK -- Simple Learned Keypointscited by 54
  27. 2020GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Networkcited by 53
  28. 2022The Lie Derivative for Measuring Learned Equivariancecited by 51
  29. 2023Self-supervised learning of Split Invariant Equivariant representationscited by 41
  30. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  31. 2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
  32. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  33. 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matchingcited by 29
  34. 2022A case for using rotation invariant features in state of the art feature matcherscited by 27
  35. 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
  36. 2023Structuring Representation Geometry with Rotationally Equivariant Contrastive Learningcited by 24
  37. 2015WxBS: Wide Baseline Stereo Generalizationscited by 23
  38. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 12
  2. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  3. 2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognitioncited by 3
  4. 2026Who Handles Orientation? Investigating Invariance in Feature Matchingcited by 1
  5. 2026CrossFeat: Bridging Imaging Modalities in Feature Descriptor Spacecited by 0
  6. 2026RoES: Rotational Equivariant Selective-frequency Fusion for Multimodal Imagescited by 0