mlsanityData to 7 Oct 2026

Adaptive Spot-Guided Transformer for Consistent Local Feature Matching

arXiv 2303.16624 ↗First posted 29 Mar 2023cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Local feature matching aims at finding correspondences between a pair of images. Although current detector-free methods leverage Transformer architecture to obtain an impressive performance, few works consider maintaining local consistency. Meanwhile, most methods struggle with large scale variations. To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture. The proposed ASTR enjoys several merits. First, we design a spot-guided aggregation module to avoid interfering with irrelevant areas during feature aggregation. Second, we design an adaptive scaling module to adjust the size of grids according to the calculated depth information at fine stage. Extensive experimental results on five standard benchmarks demonstrate that our ASTR performs favorably against state-of-the-art methods. Our code will be released on https://astr2023.github.io.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 48 of its 72 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

48 of 72 references.

References · 48

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  10. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  11. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  12. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
36 more
  1. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  4. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  5. 2020DISK: Learning local features with policy gradientcited by 310
  6. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  7. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  8. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  9. 2018Neighbourhood Consensus Networkscited by 173
  10. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  11. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  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. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 129
  16. 2022QuadTree Attention for Vision Transformerscited by 129
  17. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 128
  18. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  19. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  20. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  21. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  22. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  23. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  24. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  25. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  26. 2020Dual-Resolution Correspondence Networkscited by 90
  27. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  28. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  29. 2021Viewpoint Invariant Dense Matching for Visual Geolocalizationcited by 36
  30. 2020DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregationcited by 33
  31. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31
  32. 2022Adaptive Assignment for Geometry Aware Local Feature Matchingcited by 30
  33. 2022Guide Local Feature Matching by Overlap Estimationcited by 24
  34. 2020HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learningcited by 13
  35. 2021ScaleNet: A Shallow Architecture for Scale Estimationcited by 12
  36. 2018InLoc: Indoor Visual Localization with Dense Matching and View Synthesiscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 8; 2025: 3; 2026: 5.

22 papers.

Sort:

By area:

  1. 2023RoMa: Robust Dense Feature Matchingcited by 296
  2. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 62
  3. 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
  4. 2024MESA: Matching Everything by Segmenting Anythingcited by 16
  5. 2023Segment Anything Model is a Good Teacher for Local Feature Learningcited by 15
  6. 2023TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matchingcited by 10
  7. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  8. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  9. 2024Affine steerers for structured keypoint descriptioncited by 6
  10. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  11. 2024PRISM: PRogressive dependency maxImization for Scale-invariant image Matchingcited by 5
  12. 2024A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registrationcited by 4
10 more
  1. 2025Learning Dense Feature Matching via Lifting Single 2D Image to 3D Spacecited by 4
  2. 2023LGFCTR: Local and Global Feature Convolutional Transformer for Image Matchingcited by 1
  3. 2024Robust Two-View Geometry Estimation with Implicit Differentiationcited by 1
  4. 2025Handling Multiple Hypotheses in Coarse-to-Fine Dense Image Matchingcited by 1
  5. 2026SceneGlue: Scene-Aware Transformer for Feature Matching without Scene-Level Annotationcited by 1
  6. 2024Matching Semantically Similar Non-Identical Objectscited by 0
  7. 2026Improving Local Feature Matching by Entropy-inspired Scale Adaptability and Flow-endowed Local Consistencycited by 0
  8. 2026Cross-Modality Feature Fusion Based on Structured State Space Duality for Multimodal Image Registration Networkcited by 0
  9. 2026REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matchingcited by 0
  10. 2026Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectivescited by 0