mlsanityData to 14 Oct 2026

LIFT: Learned Invariant Feature Transform

arXiv 1603.09114 ↗First posted 30 Mar 2016cs.CVcited by 306

Not on the map. Why?

Abstract (arXiv)

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

Key facts. Cited by 306 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 60; 2022: 54; 2023: 67; 2024: 44; 2025: 50; 2026: 31.

306 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  4. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  5. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  6. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 301
  7. 20243D Reconstruction with Spatial Memorycited by 277
  8. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  9. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  10. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  11. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 200
  12. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
38 more
  1. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  2. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  3. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  4. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  5. 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
  6. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  7. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  8. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  9. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 100
  10. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  11. 2023Segment Anything Meets Point Trackingcited by 81
  12. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  13. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  14. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
  15. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  16. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  17. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  18. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 56
  19. 2021DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Featurescited by 54
  20. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  21. 2024XoFTR: Cross-modal Feature Matching Transformercited by 48
  22. 2022Correlation Verification for Image Retrievalcited by 47
  23. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  24. 2025Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstructioncited by 44
  25. 2021P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matchingcited by 42
  26. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  27. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 37
  28. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
  29. 2022BALF: Simple and Efficient Blur Aware Local Feature Detectorcited by 34
  30. 2022AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shiftcited by 32
  31. 2022TopicFM: Robust and Interpretable Topic-Assisted Feature Matchingcited by 32
  32. 2023Doppelgangers: Learning to Disambiguate Images of Similar Structurescited by 32
  33. 2024Reconstructing People, Places, and Camerascited by 31
  34. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 31
  35. 2021Deep Matching Prior: Test-Time Optimization for Dense Correspondencecited by 30
  36. 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matchingcited by 29
  37. 2021Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projectioncited by 28
  38. 2022Decoupling Makes Weakly Supervised Local Feature Bettercited by 28

50 most cited of 306 All 306 (JSON)