S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction
Not on the map. Why?
Abstract (arXiv)
In this work we introduce S-TREK, a novel local feature extractor that combines a deep keypoint detector, which is both translation and rotation equivariant by design, with a lightweight deep descriptor extractor. We train the S-TREK keypoint detector within a framework inspired by reinforcement learning, where we leverage a sequential procedure to maximize a reward directly related to keypoint repeatability. Our descriptor network is trained following a "detect, then describe" approach, where the descriptor loss is evaluated only at those locations where keypoints have been selected by the already trained detector. Extensive experiments on multiple benchmarks confirm the effectiveness of our proposed method, with S-TREK often outperforming other state-of-the-art methods in terms of repeatability and quality of the recovered poses, especially when dealing with in-plane rotations.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 28 Aug 2023.
Builds on
26 of 48 references.
References · 26
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
- 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
- 2016Group Equivariant Convolutional Networkscited by 1,165
- 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
- 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
- 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
14 more
- 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 264
- 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
- 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
- 2014TILDE: A Temporally Invariant Learned DEtectorcited by 55
- 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
- 2019Beyond Cartesian Representations for Local Descriptorscited by 35
- 2022Self-Supervised Equivariant Learning for Oriented Keypoint Detectioncited by 26
- 2022MD-Net: Multi-Detector for Local Feature Extractioncited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 6.
14 papers.
Sort:
By area:
- 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
- 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 26
- 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
- 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detectioncited by 13
- 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
- 2024Affine steerers for structured keypoint descriptioncited by 6
- 2024GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoringcited by 5
- 2024Image Matching Filtering and Refinement by Planes and Beyondcited by 5
- 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
- 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2
- 2026TerraSky3D: Multi-View Reconstructions of European Landmarks in 4Kcited by 2
- 2026From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detectioncited by 0
2 more
- 2026RIPE++: Reinforced Keypoint Learning from Positive Pairs Onlycited by 0
- 2026On Making SE(2)-Invariant Networks Optimalcited by 0
- 2026On Making SE(2)-Invariant Networks Optimal12 Oct 2026
- 2026RIPE++: Reinforced Keypoint Learning from Positive Pairs Only20 Aug 2026
- 2026TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K30 Mar 2026
- 2026From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection24 Feb 2026
- 2026RaCo: Ranking and Covariance for Practical Learned Keypoints17 Feb 2026
- 2026A Streamlined Attention-Based Network for Descriptor Extraction19 Jan 2026
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025
- 2025DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection10 Mar 2025
- 2024Image Matching Filtering and Refinement by Planes and Beyond14 Nov 2024
- 2024GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring30 Aug 2024
- 2024Affine steerers for structured keypoint description26 Aug 2024
- 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences9 Apr 2024
2 more
- 2024Local Feature Matching Using Deep Learning: A Surveycited by 26
- 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondencescited by 26
- 2023Steerers: A framework for rotation equivariant keypoint descriptorscited by 21
- 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
- 2024Affine steerers for structured keypoint descriptioncited by 6
- 2024GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoringcited by 5
- 2024Image Matching Filtering and Refinement by Planes and Beyondcited by 5
- 2026RaCo: Ranking and Covariance for Practical Learned Keypointscited by 3
- 2026A Streamlined Attention-Based Network for Descriptor Extractioncited by 2
- 2026TerraSky3D: Multi-View Reconstructions of European Landmarks in 4Kcited by 2
- 2026RIPE++: Reinforced Keypoint Learning from Positive Pairs Onlycited by 0
- 2026On Making SE(2)-Invariant Networks Optimalcited by 0
- 2026On Making SE(2)-Invariant Networks Optimal12 Oct 2026
- 2026RIPE++: Reinforced Keypoint Learning from Positive Pairs Only20 Aug 2026
- 2026TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K30 Mar 2026
- 2026RaCo: Ranking and Covariance for Practical Learned Keypoints17 Feb 2026
- 2026A Streamlined Attention-Based Network for Descriptor Extraction19 Jan 2026
- 2025Deep Learning Reforms Image Matching: A Survey and Outlook5 Jun 2025
- 2024Image Matching Filtering and Refinement by Planes and Beyond14 Nov 2024
- 2024GMM-IKRS: Gaussian Mixture Models for Interpretable Keypoint Refinement and Scoring30 Aug 2024
- 2024Affine steerers for structured keypoint description26 Aug 2024
- 2024Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences9 Apr 2024
- 2024Local Feature Matching Using Deep Learning: A Survey31 Jan 2024
- 2023Steerers: A framework for rotation equivariant keypoint descriptors4 Dec 2023