mlsanityData to 7 Oct 2026

ScaleNet: A Shallow Architecture for Scale Estimation

arXiv 2112.04846 ↗First posted 9 Dec 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, ScaleNet, that exploits dilated convolutions as well as self and cross-correlation layers to predict the scale between images. We demonstrate that rectifying images with estimated scales leads to significant performance improvements for various tasks and methods. Specifically, we show how ScaleNet can be combined with sparse local features and dense correspondence networks to improve camera pose estimation, 3D reconstruction, or dense geometric matching in different benchmarks and datasets. We provide an extensive evaluation on several tasks and analyze the computational overhead of ScaleNet. The code, evaluation protocols, and trained models are publicly available at https://github.com/axelBarroso/ScaleNet.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

46 of 61 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2015Spatial Transformer Networkscited by 1,423
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  11. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  12. 2016LIFT: Learned Invariant Feature Transformcited by 305
34 more
  1. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  2. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  3. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  4. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  5. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  6. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  7. 2017Learning to Find Good Correspondencescited by 176
  8. 2018LF-Net: Learning Local Features from Imagescited by 151
  9. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  10. 2017Convolutional neural network architecture for geometric matchingcited by 138
  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. 2018MAGSAC: marginalizing sample consensuscited by 122
  15. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  16. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  17. 2018DGC-Net: Dense Geometric Correspondence Networkcited by 67
  18. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  19. 2020GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Networkcited by 53
  20. 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
  21. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  22. 2020Online Invariance Selection for Local Feature Descriptorscited by 41
  23. 2019Beyond Cartesian Representations for Local Descriptorscited by 35
  24. 2020D2D: Keypoint Extraction with Describe to Detect Approachcited by 34
  25. 2015MODS: Fast and Robust Method for Two-View Matchingcited by 26
  26. 2020Multi-View Optimization of Local Feature Geometrycited by 24
  27. 2020S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matchingcited by 22
  28. 2020Single-Image Depth Prediction Makes Feature Matching Easiercited by 21
  29. 2015Learning to Assign Orientations to Feature Pointscited by 16
  30. 2020Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddingscited by 16
  31. 2020HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learningcited by 13
  32. 2019VIZARD: Reliable Visual Localization for Autonomous Vehicles in Urban Outdoor Environmentscited by 9
  33. 2018Large scale evaluation of local image feature detectors on homography datasetscited by 4
  34. 2020HyNet: Learning Local Descriptor with Hybrid Similarity Measure and Triplet Losscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 3; 2025: 2; 2026: 1.

12 papers.

  1. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  2. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  3. 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 25
  4. 2023Learning Rotation-Equivariant Features for Visual Correspondencecited by 23
  5. 2023Adaptive Spot-Guided Transformer for Consistent Local Feature Matchingcited by 22
  6. 2023Two-View Geometry Scoring Without Correspondencescited by 11
  7. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  8. 2024Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switchingcited by 7
  9. 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypothesescited by 6
  10. 2025A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Featurescited by 4
  11. 2025Local Scale Equivariance with Latent Deep Equilibrium Canonicalizercited by 2
  12. 2026DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual Localizationcited by 0