mlsanityData to 7 Oct 2026

Self-Supervised Learning of Image Scale and Orientation

arXiv 2206.07259 ↗First posted 15 Jun 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

We study the problem of learning to assign a characteristic pose, i.e., scale and orientation, for an image region of interest. Despite its apparent simplicity, the problem is non-trivial; it is hard to obtain a large-scale set of image regions with explicit pose annotations that a model directly learns from. To tackle the issue, we propose a self-supervised learning framework with a histogram alignment technique. It generates pairs of image patches by random rescaling/rotating and then train an estimator to predict their scale/orientation values so that their relative difference is consistent with the rescaling/rotating used. The estimator learns to predict a non-parametric histogram distribution of scale/orientation without any supervision. Experiments show that it significantly outperforms previous methods in scale/orientation estimation and also improves image matching and 6 DoF camera pose estimation by incorporating our patch poses into a matching process.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 15 Jun 2022.

Builds on

25 of 51 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  5. 2015Spatial Transformer Networkscited by 1,423
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  7. 2016LIFT: Learned Invariant Feature Transformcited by 305
  8. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  9. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  10. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  11. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  12. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
13 more
  1. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 189
  2. 2018LF-Net: Learning Local Features from Imagescited by 151
  3. 2019SPair-71k: A Large-scale Benchmark for Semantic Correspondencecited by 140
  4. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  5. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  6. 2019SFNet: Learning Object-aware Semantic Correspondencecited by 60
  7. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  8. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  9. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  10. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  11. 2014Do Convnets Learn Correspondence?cited by 28
  12. 2019RF-Net: An End-to-End Image Matching Network based on Receptive Fieldcited by 22
  13. 2015Learning to Assign Orientations to Feature Pointscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 1; 2026: 1.

9 papers.

  1. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  2. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  3. 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
  4. 2024Affine steerers for structured keypoint descriptioncited by 6
  5. 2023AffineGlue: Joint Matching and Robust Estimationcited by 5
  6. 2023RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopycited by 5
  7. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  8. 2025Local Scale Equivariance with Latent Deep Equilibrium Canonicalizercited by 2
  9. 2026Who Handles Orientation? Investigating Invariance in Feature Matchingcited by 1