# DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching

arXiv: https://arxiv.org/abs/2308.08479 · HTML: https://mlsanity.com/paper/2308.08479/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 16 Aug 2023.

## Builds on (most cited first, 29 of 29)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [LIFT: Learned Invariant Feature Transform](https://mlsanity.com/paper/1603.09114/) (2016)
- [Working hard to know your neighbor's margins: Local descriptor learning loss](https://mlsanity.com/paper/1705.10872/) (2017)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [MatchFormer: Interleaving Attention in Transformers for Feature Matching](https://mlsanity.com/paper/2203.09645/) (2022)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters](https://mlsanity.com/paper/1904.00889/) (2019)
- [Learning to Match Features with Seeded Graph Matching Network](https://mlsanity.com/paper/2108.08771/) (2021)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [Repeatability Is Not Enough: Learning Affine Regions via Discriminability](https://mlsanity.com/paper/1711.06704/) (2017)
- [TILDE: A Temporally Invariant Learned DEtector](https://mlsanity.com/paper/1411.4568/) (2014)
- [SiLK -- Simple Learned Keypoints](https://mlsanity.com/paper/2304.06194/) (2023)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [PMatch: Paired Masked Image Modeling for Dense Geometric Matching](https://mlsanity.com/paper/2303.17342/) (2023)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [A case for using rotation invariant features in state of the art feature matchers](https://mlsanity.com/paper/2204.10144/) (2022)
- [Adaptive Spot-Guided Transformer for Consistent Local Feature Matching](https://mlsanity.com/paper/2303.16624/) (2023)
- [Self-Supervised Learning of Image Scale and Orientation](https://mlsanity.com/paper/2206.07259/) (2022)

## Built on by (most cited first, 30 of 63)

- [MegaScenes: Scene-Level View Synthesis at Scale](https://mlsanity.com/paper/2406.11819/) (2024)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)
- [FG2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching](https://mlsanity.com/paper/2503.18725/) (2025)
- [Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences](https://mlsanity.com/paper/2404.06337/) (2024)
- [Steerers: A framework for rotation equivariant keypoint descriptors](https://mlsanity.com/paper/2312.02152/) (2023)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization](https://mlsanity.com/paper/2409.16502/) (2024)
- [JamMa: Ultra-lightweight Local Feature Matching with Joint Mamba](https://mlsanity.com/paper/2503.03437/) (2025)
- [EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography](https://mlsanity.com/paper/2405.05422/) (2024)
- [Learning to Make Keypoints Sub-Pixel Accurate](https://mlsanity.com/paper/2407.11668/) (2024)
- [DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection](https://mlsanity.com/paper/2503.07347/) (2025)
- [RDD: Robust Feature Detector and Descriptor using Deformable Transformer](https://mlsanity.com/paper/2505.08013/) (2025)
- [MATCHA:Towards Matching Anything](https://mlsanity.com/paper/2501.14945/) (2025)
- [OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata](https://mlsanity.com/paper/2509.18350/) (2025)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction](https://mlsanity.com/paper/2507.04839/) (2025)
- [ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training](https://mlsanity.com/paper/2510.11605/) (2025)
- [3MOS: Multi-sources, Multi-resolutions, and Multi-scenes dataset for Optical-SAR image matching](https://mlsanity.com/paper/2404.00838/) (2024)
- [Raising the Ceiling: Conflict-Free Local Feature Matching with Dynamic View Switching](https://mlsanity.com/paper/2407.07789/) (2024)
- [CoMatcher: Multi-View Collaborative Feature Matching](https://mlsanity.com/paper/2504.01872/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Affine steerers for structured keypoint description](https://mlsanity.com/paper/2408.14186/) (2024)
- [Extreme Rotation Estimation in the Wild](https://mlsanity.com/paper/2411.07096/) (2024)
- [Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence](https://mlsanity.com/paper/2410.09533/) (2024)
- [Image Matching Filtering and Refinement by Planes and Beyond](https://mlsanity.com/paper/2411.09484/) (2024)
- [Learning Affine Correspondences by Integrating Geometric Constraints](https://mlsanity.com/paper/2504.04834/) (2025)
- [Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks](https://mlsanity.com/paper/2408.16445/) (2024)
- [To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition](https://mlsanity.com/paper/2504.06116/) (2025)
- [Second-order Gaussian directional derivative representations for image high-resolution corner detection](https://mlsanity.com/paper/2601.08182/) (2026)

## Abstract (arXiv)

Keypoint detection is a pivotal step in 3D reconstruction, whereby sets of (up to) K points are detected in each view of a scene. Crucially, the detected points need to be consistent between views, i.e., correspond to the same 3D point in the scene. One of the main challenges with keypoint detection is the formulation of the learning objective. Previous learning-based methods typically jointly learn descriptors with keypoints, and treat the keypoint detection as a binary classification task on mutual nearest neighbours. However, basing keypoint detection on descriptor nearest neighbours is a proxy task, which is not guaranteed to produce 3D-consistent keypoints. Furthermore, this ties the keypoints to a specific descriptor, complicating downstream usage. In this work, we instead learn keypoints directly from 3D consistency. To this end, we train the detector to detect tracks from large-scale SfM. As these points are often overly sparse, we derive a semi-supervised two-view detection objective to expand this set to a desired number of detections. To train a descriptor, we maximize the mutual nearest neighbour objective over the keypoints with a separate network. Results show that our approach, DeDoDe, achieves significant gains on multiple geometry benchmarks. Code is provided at https://github.com/Parskatt/DeDoDe