mlsanityData to 14 Oct 2026

ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation

arXiv 2304.03608 ↗First posted 7 Apr 2023cs.CVcited by 121

Not on the map. Why?

Abstract (arXiv)

Image keypoints and descriptors play a crucial role in many visual measurement tasks. In recent years, deep neural networks have been widely used to improve the performance of keypoint and descriptor extraction. However, the conventional convolution operations do not provide the geometric invariance required for the descriptor. To address this issue, we propose the Sparse Deformable Descriptor Head (SDDH), which learns the deformable positions of supporting features for each keypoint and constructs deformable descriptors. Furthermore, SDDH extracts descriptors at sparse keypoints instead of a dense descriptor map, which enables efficient extraction of descriptors with strong expressiveness. In addition, we relax the neural reprojection error (NRE) loss from dense to sparse to train the extracted sparse descriptors. Experimental results show that the proposed network is both efficient and powerful in various visual measurement tasks, including image matching, 3D reconstruction, and visual relocalization.

Key facts. Cited by 121 papers in the map (data through 14 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

41 of 63 references.

References · 41

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  5. 2017Deformable Convolutional Networkscited by 1,488
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  7. 2015Spatial Transformer Networkscited by 1,429
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  11. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 670
  12. 2017Self-Normalizing Neural Networkscited by 598
29 more
  1. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  2. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  3. 2020DISK: Learning local features with policy gradientcited by 312
  4. 2016LIFT: Learned Invariant Feature Transformcited by 306
  5. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
  6. 2017Integral Human Pose Regressioncited by 256
  7. 2018TDAN: Temporally Deformable Alignment Network for Video Super-Resolutioncited by 226
  8. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  9. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
  10. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  11. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  12. 2018LF-Net: Learning Local Features from Imagescited by 151
  13. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  14. 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
  15. 2016Universal Correspondence Networkcited by 82
  16. 2020Understanding Deformable Alignment in Video Super-Resolutioncited by 78
  17. 2021ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extractioncited by 77
  18. 2017Repeatability Is Not Enough: Learning Affine Regions via Discriminabilitycited by 57
  19. 2018Object Detection in Video with Spatiotemporal Sampling Networkscited by 57
  20. 2021ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imagingcited by 51
  21. 2019GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNscited by 47
  22. 2020D2D: Keypoint Extraction with Describe to Detect Approachcited by 34
  23. 2019An Evaluation of Feature Matchers for Fundamental Matrix Estimationcited by 18
  24. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  25. 2020HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learningcited by 13
  26. 2020SEKD: Self-Evolving Keypoint Detection and Descriptioncited by 11
  27. 2021Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Networkcited by 8
  28. 2021Novel Intensity Mapping Functions: Weighted Histogram Averagingcited by 3
  29. 2021Automatic Vocabulary and Graph Verification for Accurate Loop Closure Detectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 19; 2025: 36; 2026: 62.

121 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  3. 2023Dense Optical Tracking: Connecting the Dotscited by 61
  4. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 51
  5. 2024DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detectorcited by 39
  6. 2026VGGT-Omegacited by 26
  7. 2024The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinementcited by 21
  8. 2025Relative Pose Estimation through Affine Corrections of Monocular Depth Priorscited by 18
  9. 2023Unlocking the Use of Raw Multispectral Earth Observation Imagery for Onboard Artificial Intelligencecited by 14
  10. 2025Benchmarking Egocentric Visual-Inertial SLAM at City Scalecited by 14
  11. 2024EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photographycited by 13
  12. 2024Learning to Make Keypoints Sub-Pixel Accuratecited by 13
38 more
  1. 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 13
  2. 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformercited by 13
  3. 2025CoMatch: Dynamic Covisibility-Aware Transformer for Bilateral Subpixel-Level Semi-Dense Image Matchingcited by 12
  4. 2026LoMa: Local Feature Matching Revisitedcited by 11
  5. 2025Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regressioncited by 10
  6. 2025From Monocular Vision to Autonomous Action: Guiding Tumor Resection via 3D Reconstructioncited by 10
  7. 2024WildFusion: Individual Animal Identification with Calibrated Similarity Fusioncited by 9
  8. 2025A Guide to Structureless Visual Localizationcited by 9
  9. 2025RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extractioncited by 9
  10. 2025RUBIK: A Structured Benchmark for Image Matching across Geometric Challengescited by 8
  11. 2026Global Structure-from-Motion Meets Feedforward Reconstructioncited by 8
  12. 2024Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switchingcited by 7
  13. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  14. 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Viewscited by 7
  15. 2024Affine steerers for structured keypoint descriptioncited by 6
  16. 2025MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matchingcited by 6
  17. 2023RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopycited by 5
  18. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  19. 2024Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondencecited by 5
  20. 2024Image Matching Filtering and Refinement by Planes and Beyondcited by 5
  21. 2025A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Featurescited by 5
  22. 2024Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarkscited by 4
  23. 2025Keypoint Detection and Description for Raw Bayer Imagescited by 4
  24. 2025Unsupervised Pelage Pattern Unwrapping for Animal Re-identificationcited by 4
  25. 2024Geometry-Aware Feature Matching for Large-Scale Structure from Motioncited by 3
  26. 2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognitioncited by 3
  27. 2025A 3D Cross-modal Keypoint Descriptor for MR-US Matching and Registrationcited by 3
  28. 2026Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardwarecited by 3
  29. 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
  30. 2024Scale-Free Image Keypoints Using Differentiable Persistent Homologycited by 2
  31. 2024On Model-Free Re-ranking for Visual Place Recognition with Deep Learned Local Featurescited by 2
  32. 20253D Gaussian Splatting aided Localization for Large and Complex Indoor-Environmentscited by 2
  33. 2025Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparisoncited by 2
  34. 2025Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Imagescited by 2
  35. 2025CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenescited by 2
  36. 2025ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environmentscited by 2
  37. 2025LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matchingcited by 2
  38. 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2

50 most cited of 121 All 121 (JSON)