ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction
Not on the map. Why?
Abstract (arXiv)
Existing methods detect the keypoints in a non-differentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a partially differentiable keypoint detection module, which outputs accurate sub-pixel keypoints. The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization. We also extract the descriptors in a sub-pixel way, and they are trained with the stable neural reprojection error loss. Moreover, a lightweight network is designed for keypoint detection and descriptor extraction, which can run at 95 frames per second for 640x480 images on a commercial GPU. On homography estimation, camera pose estimation, and visual (re-)localization tasks, the proposed method achieves equivalent performance with the state-of-the-art approaches, while greatly reduces the inference time.
Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). Builds on 31 of its 52 references that are in the map. First posted on arXiv 6 Dec 2021.
Builds on
31 of 52 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
- 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
- 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
- 2020DISK: Learning local features with policy gradientcited by 312
- 2016LIFT: Learned Invariant Feature Transformcited by 306
- 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
- 2017Integral Human Pose Regressioncited by 256
- 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
- 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
19 more
- 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 207
- 2018LF-Net: Learning Local Features from Imagescited by 151
- 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
- 2020ASLFeat: Learning Local Features of Accurate Shape and Localizationcited by 130
- 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 118
- 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
- 2020VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Changecited by 101
- 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
- 2018Local Descriptors Optimized for Average Precisioncited by 43
- 2019Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Taskcited by 39
- 2016Quad-networks: unsupervised learning to rank for interest point detectioncited by 36
- 2020D2D: Keypoint Extraction with Describe to Detect Approachcited by 34
- 2020S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matchingcited by 23
- 2019Sparse-to-Dense Hypercolumn Matching for Long-Term Visual Localizationcited by 20
- 2020UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervisioncited by 17
- 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
- 2020HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learningcited by 13
- 2020SEKD: Self-Evolving Keypoint Detection and Descriptioncited by 11
- 2018Dual-mode Dynamic Window Approach to Robot Navigation with Convergence Guaranteescited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 5; 2023: 10; 2024: 19; 2025: 17; 2026: 25.
77 papers.
Sort:
By area:
- 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
- 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
- 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
- 2024DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detectorcited by 39
- 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
- 2024MESA: Matching Everything by Segmenting Anythingcited by 16
- 2023Segment Anything Model is a Good Teacher for Local Feature Learningcited by 15
- 2024EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photographycited by 13
- 2024Learning to Make Keypoints Sub-Pixel Accuratecited by 13
- 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 13
- 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformercited by 13
- 2025LiftFeat: 3D Geometry-Aware Local Feature Matchingcited by 12
38 more
- 2026LoMa: Local Feature Matching Revisitedcited by 11
- 2022FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Networkcited by 10
- 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
- 2025A Guide to Structureless Visual Localizationcited by 9
- 20243MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matchingcited by 8
- 2022Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Networkcited by 7
- 2023OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matchingcited by 7
- 2025EDM: Efficient Deep Feature Matchingcited by 7
- 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
- 2024Affine steerers for structured keypoint descriptioncited by 6
- 2025MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matchingcited by 6
- 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
- 2024Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondencecited by 5
- 2024Image Matching Filtering and Refinement by Planes and Beyondcited by 5
- 2023Breaking of brightness consistency in optical flow with a lightweight CNN networkcited by 4
- 2024Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarkscited by 4
- 2025Keypoint Detection and Description for Raw Bayer Imagescited by 4
- 2024MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentationcited by 3
- 2026Second-order Gaussian directional derivative representations for image high-resolution corner detectioncited by 3
- 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
- 2022Descriptor Distillation: a Teacher-Student-Regularized Framework for Learning Local Descriptorscited by 2
- 2023FMRT: Learning Accurate Feature Matching with Reconciliatory Transformercited by 2
- 2024Scale-Free Image Keypoints Using Differentiable Persistent Homologycited by 2
- 2025Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparisoncited by 2
- 2025Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Imagescited by 2
- 2025LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matchingcited by 2
- 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2
- 2021Sparse LiDAR Assisted Self-supervised Stereo Disparity Estimationcited by 1
- 2023Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch Invariancecited by 1
- 2023Improving the matching of deformable objects by learning to detect keypointscited by 1
- 2024Neural Augmentation Based Panoramic High Dynamic Range Stitchingcited by 1
- 2024FaVoR: Features via Voxel Rendering for Camera Relocalizationcited by 1
- 2024BiDense: Binarization for Dense Predictioncited by 1
- 2025EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracycited by 1
- 2025CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidancecited by 1
- 2026ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matchingcited by 1
- 2026GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergycited by 1
- 2026Argus: Metric Panoramic 3D Reconstruction for Indoor Scenescited by 1
50 most cited of 77 All 77 (JSON)
- 2026RoMa-Omega: What Feed-Forward 3D Models Know About Image Matching8 Sep 2026
- 2026NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry5 Sep 2026
- 2026Misanthrope: A Privacy-Preserving Keypoint Detector24 Aug 2026
- 2026DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual Localization23 Aug 2026
- 2026Unified and Efficient Point-Line Local Features20 Aug 2026
- 2026Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives11 Aug 2026
- 2026XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher10 Aug 2026
- 2026Accuracy potential of visual localization exploiting high-end street-level imagery27 Jul 2026
- 2026SLAM in Low-Light Environments: Project Report20 Jul 2026
- 2026Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems13 Jul 2026
- 2026Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes29 Jun 2026
- 2026HyKey: Hyperspectral Keypoint Detection and Matching in Minimally Invasive Surgery19 Apr 2026
38 more
- 2026Privacy-Preserving Structureless Visual Localization via Image Obfuscation13 Apr 2026
- 2026AsymLoc: Towards Asymmetric Feature Matching for Efficient Visual Localization10 Apr 2026
- 2026GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy7 Apr 2026
- 2026LoMa: Local Feature Matching Revisited6 Apr 2026
- 2026ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matching3 Apr 2026
- 2026Scene Representation using 360deg Saliency Graph and its Application in Vision-based Indoor Navigation20 Mar 2026
- 2026No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors26 Feb 2026
- 2026From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection24 Feb 2026
- 2026RaCo: Ranking and Covariance for Practical Learned Keypoints17 Feb 2026
- 2026Coarse-to-Fine Non-rigid Multi-modal Image Registration for Historical Panel Paintings based on Crack Structures22 Jan 2026
- 2026A Streamlined Attention-Based Network for Descriptor Extraction19 Jan 2026
- 2026CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation14 Jan 2026
- 2026Second-order Gaussian directional derivative representations for image high-resolution corner detection13 Jan 2026
- 2025Adaptive Covariance and Quaternion-Focused Hybrid Error-State EKF/UKF for Visual-Inertial Odometry19 Dec 2025
- 2025LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching18 Oct 2025
- 2025PIVOTS: Aligning unseen Structures using Preoperative to Intraoperative Volume-To-Surface Registration for Liver Navigation27 Jul 2025
- 2025CasP: Improving Semi-Dense Feature Matching Pipeline Leveraging Cascaded Correspondence Priors for Guidance23 Jul 2025
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025
- 2025Why Not Replace? Sustaining Long-Term Visual Localization via Handcrafted-Learned Feature Collaboration on CPU24 May 2025
- 2025GMatch: A Lightweight, Geometry-Constrained Keypoint Matcher for Zero-Shot 6DoF Pose Estimation in Robotic Grasp Tasks22 May 2025
- 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformer12 May 2025
- 2025LiftFeat: 3D Geometry-Aware Local Feature Matching6 May 2025
- 2025A Guide to Structureless Visual Localization24 Apr 2025
- 2025EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracy24 Apr 2025
- 2025Knowledge Distillation for Underwater Feature Extraction and Matching via GAN-synthesized Images11 Apr 2025
- 2025Keypoint Detection and Description for Raw Bayer Images11 Mar 2025
- 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection10 Mar 2025
- 2025EDM: Efficient Deep Feature Matching7 Mar 2025
- 2025Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison27 Feb 2025
- 2025MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching20 Jan 2025
- 2024BiDense: Binarization for Dense Prediction15 Nov 2024
- 2024Image Matching Filtering and Refinement by Planes and Beyond14 Nov 2024
- 2024Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence12 Oct 2024
- 2024FaVoR: Features via Voxel Rendering for Camera Relocalization11 Sep 2024
- 2024Neural Augmentation Based Panoramic High Dynamic Range Stitching7 Sep 2024
- 2024Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks29 Aug 2024
- 2024Affine steerers for structured keypoint description26 Aug 2024
- 2024MESA: Effective Matching Redundancy Reduction by Semantic Area Segmentation1 Aug 2024
50 newest of 77 All 77 (JSON)
- 2023ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformationcited by 121
- 2024XFeat: Accelerated Features for Lightweight Image Matchingcited by 113
- 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
- 2024DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detectorcited by 39
- 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
- 2024MESA: Matching Everything by Segmenting Anythingcited by 16
- 2023Segment Anything Model is a Good Teacher for Local Feature Learningcited by 15
- 2024EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photographycited by 13
- 2024Learning to Make Keypoints Sub-Pixel Accuratecited by 13
- 2025RDD: Robust Feature Detector and Descriptor using Deformable Transformercited by 13
- 2025LiftFeat: 3D Geometry-Aware Local Feature Matchingcited by 12
- 2026LoMa: Local Feature Matching Revisitedcited by 11
12 most cited of 73 All 73 (JSON)
- 2026RoMa-Omega: What Feed-Forward 3D Models Know About Image Matching8 Sep 2026
- 2026NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry5 Sep 2026
- 2026Misanthrope: A Privacy-Preserving Keypoint Detector24 Aug 2026
- 2026DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual Localization23 Aug 2026
- 2026Unified and Efficient Point-Line Local Features20 Aug 2026
- 2026Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives11 Aug 2026
- 2026XFeat Revisited: Reproducibility and Evaluation of a Lightweight Image Matcher10 Aug 2026
- 2026Accuracy potential of visual localization exploiting high-end street-level imagery27 Jul 2026
- 2026SLAM in Low-Light Environments: Project Report20 Jul 2026
- 2026Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems13 Jul 2026
- 2026Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes29 Jun 2026
- 2026HyKey: Hyperspectral Keypoint Detection and Matching in Minimally Invasive Surgery19 Apr 2026
12 newest of 73 All 73 (JSON)