mlsanityData to 14 Oct 2026

SuperPoint: Self-Supervised Interest Point Detection and Description

arXiv 1712.07629 ↗First posted 20 Dec 2017cs.CVcited by 1,320

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision. As opposed to patch-based neural networks, our fully-convolutional model operates on full-sized images and jointly computes pixel-level interest point locations and associated descriptors in one forward pass. We introduce Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation (e.g., synthetic-to-real). Our model, when trained on the MS-COCO generic image dataset using Homographic Adaptation, is able to repeatedly detect a much richer set of interest points than the initial pre-adapted deep model and any other traditional corner detector. The final system gives rise to state-of-the-art homography estimation results on HPatches when compared to LIFT, SIFT and ORB.

Key facts. Cited by 1,320 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 133; 2022: 172; 2023: 229; 2024: 228; 2025: 301; 2026: 257.

1,320 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  3. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  5. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  6. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  8. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  9. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  10. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  11. 2023Emergent Correspondence from Image Diffusioncited by 446
  12. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
38 more
  1. 2023RoMa: Robust Dense Feature Matchingcited by 302
  2. 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 287
  3. 20243D Reconstruction with Spatial Memorycited by 277
  4. 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 263
  5. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  6. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  7. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  8. 2024Global Structure-from-Motion Revisitedcited by 218
  9. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  10. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  11. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  12. 2023Tracking Everything Everywhere All at Oncecited by 193
  13. 2022Deep Patch Visual Odometrycited by 190
  14. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  15. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  16. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  17. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  18. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  19. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  20. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  21. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  22. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  23. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  24. 2021Learning Target Candidate Association to Keep Track of What Not to Trackcited by 131
  25. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  26. 2022QuadTree Attention for Vision Transformerscited by 129
  27. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
  28. 2024CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videoscited by 128
  29. 2022MatchFormer: Interleaving Attention in Transformers for Feature Matchingcited by 126
  30. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
  31. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  32. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 120
  33. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  34. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  35. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  36. 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
  37. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  38. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102

50 most cited of 1,320 All 1,320 (JSON)