mlsanityData to 13 Oct 2026

Convolutional neural network architecture for geometric matching

arXiv 1703.05593 ↗First posted 16 Mar 2017cs.CV cs.LGcited by 138

Not on the map. Why?

Abstract (arXiv)

We address the problem of determining correspondences between two images in agreement with a geometric model such as an affine or thin-plate spline transformation, and estimating its parameters. The contributions of this work are three-fold. First, we propose a convolutional neural network architecture for geometric matching. The architecture is based on three main components that mimic the standard steps of feature extraction, matching and simultaneous inlier detection and model parameter estimation, while being trainable end-to-end. Second, we demonstrate that the network parameters can be trained from synthetically generated imagery without the need for manual annotation and that our matching layer significantly increases generalization capabilities to never seen before images. Finally, we show that the same model can perform both instance-level and category-level matching giving state-of-the-art results on the challenging Proposal Flow dataset.

Key facts. Cited by 138 papers in the map (data through 13 Oct 2026). First posted on arXiv 16 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 40; 2022: 34; 2023: 22; 2024: 16; 2025: 16; 2026: 10.

138 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 440
  2. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 298
  3. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 217
  4. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  5. 2022Dress Code: High-Resolution Multi-Category Virtual Try-Oncited by 161
  6. 2023LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-Oncited by 151
  7. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  8. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  9. 2023SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentationcited by 97
  10. 2022NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fieldscited by 86
  11. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  12. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
38 more
  1. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  2. 2024Local All-Pair Correspondence for Point Trackingcited by 78
  3. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  4. 2023Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editingcited by 62
  5. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  6. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  7. 2023Continuous Sign Language Recognition with Correlation Networkcited by 56
  8. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  9. 2021Convolutional Hough Matching Networkscited by 43
  10. 2021Warp Consistency for Unsupervised Learning of Dense Correspondencescited by 42
  11. 2023Diversity-Measurable Anomaly Detectioncited by 41
  12. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  13. 2021Viewpoint Invariant Dense Matching for Visual Geolocalizationcited by 36
  14. 2023Geometric Visual Similarity Learning in 3D Medical Image Self-supervised Pre-trainingcited by 36
  15. 2021Toward Accurate and Realistic Outfits Visualization with Attention to Detailscited by 33
  16. 2021Multi-scale Matching Networks for Semantic Correspondencecited by 32
  17. 2022Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondencecited by 32
  18. 2021M3D-VTON: A Monocular-to-3D Virtual Try-On Networkcited by 31
  19. 2022Learning Semantic Correspondence with Sparse Annotationscited by 31
  20. 2021Deep Matching Prior: Test-Time Optimization for Dense Correspondencecited by 30
  21. 2022Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondencescited by 30
  22. 2023Neural Congealing: Aligning Images to a Joint Semantic Atlascited by 30
  23. 2022TransforMatcher: Match-to-Match Attention for Semantic Correspondencecited by 29
  24. 2022C-VTON: Context-Driven Image-Based Virtual Try-On Networkcited by 29
  25. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  26. 2023ASIC: Aligning Sparse in-the-wild Image Collectionscited by 26
  27. 2022MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translationcited by 22
  28. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
  29. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  30. 2022Model-Agnostic Augmentation for Accurate Graph Classificationcited by 21
  31. 2023Diffusion Model for Dense Matchingcited by 21
  32. 2021The Functional Correspondence Problemcited by 20
  33. 2022Stand-Alone Inter-Frame Attention in Video Modelscited by 19
  34. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 19
  35. 2021WAS-VTON: Warping Architecture Search for Virtual Try-on Networkcited by 18
  36. 2021DFM: A Performance Baseline for Deep Feature Matchingcited by 17
  37. 2022CoordGAN: Self-Supervised Dense Correspondences Emerge from GANscited by 17
  38. 2024Distillation of Diffusion Features for Semantic Correspondencecited by 17

50 most cited of 138 All 138 (JSON)