# Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters

arXiv: https://arxiv.org/abs/1904.00889 · HTML: https://mlsanity.com/paper/1904.00889/

## Key facts

- Cited by 118 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2019.

## Built on by (most cited first, 30 of 118)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [Correlation Verification for Image Retrieval](https://mlsanity.com/paper/2204.01458/) (2022)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [Planar Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2103.14644/) (2021)
- [DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector](https://mlsanity.com/paper/2404.08928/) (2024)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)
- [Adaptive Assignment for Geometry Aware Local Feature Matching](https://mlsanity.com/paper/2207.08427/) (2022)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [Self-Supervised Equivariant Learning for Oriented Keypoint Detection](https://mlsanity.com/paper/2204.08613/) (2022)
- [ReDFeat: Recoupling Detection and Description for Multimodal Feature Learning](https://mlsanity.com/paper/2205.07439/) (2022)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [A Robust and Interpretable Deep Learning Framework for Multi-modal Registration via Keypoints](https://mlsanity.com/paper/2304.09941/) (2023)
- [Adaptive Spot-Guided Transformer for Consistent Local Feature Matching](https://mlsanity.com/paper/2303.16624/) (2023)
- [NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning](https://mlsanity.com/paper/2112.12785/) (2021)
- [Partially Does It: Towards Scene-Level FG-SBIR with Partial Input](https://mlsanity.com/paper/2203.14804/) (2022)
- [ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement](https://mlsanity.com/paper/2209.12213/) (2022)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [MESA: Matching Everything by Segmenting Anything](https://mlsanity.com/paper/2401.16741/) (2024)
- [Segment Anything Model is a Good Teacher for Local Feature Learning](https://mlsanity.com/paper/2309.16992/) (2023)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction](https://mlsanity.com/paper/2308.14598/) (2023)

## Abstract (arXiv)

We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show that our approach outperforms state-of-the-art detectors in terms of repeatability, matching performance and complexity.