# DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector

arXiv: https://arxiv.org/abs/2404.08928 · HTML: https://mlsanity.com/paper/2404.08928/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 13 Apr 2024.

## Builds on (most cited first, 24 of 24)

- [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)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [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)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (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)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching](https://mlsanity.com/paper/2204.11700/) (2022)
- [TILDE: A Temporally Invariant Learned DEtector](https://mlsanity.com/paper/1411.4568/) (2014)
- [SiLK -- Simple Learned Keypoints](https://mlsanity.com/paper/2304.06194/) (2023)
- [Warp Consistency for Unsupervised Learning of Dense Correspondences](https://mlsanity.com/paper/2104.03308/) (2021)
- [A case for using rotation invariant features in state of the art feature matchers](https://mlsanity.com/paper/2204.10144/) (2022)
- [Steerers: A framework for rotation equivariant keypoint descriptors](https://mlsanity.com/paper/2312.02152/) (2023)
- [HarrisZ^+: Harris Corner Selection for Next-Gen Image Matching Pipelines](https://mlsanity.com/paper/2109.12925/) (2021)

## Built on by (most cited first, 30 of 39)

- [HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval](https://mlsanity.com/paper/2512.02792/) (2025)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [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)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression](https://mlsanity.com/paper/2503.07561/) (2025)
- [Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification](https://mlsanity.com/paper/2509.26614/) (2025)
- [RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges](https://mlsanity.com/paper/2502.19955/) (2025)
- [Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillation](https://mlsanity.com/paper/2510.00681/) (2025)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Image Matching Filtering and Refinement by Planes and Beyond](https://mlsanity.com/paper/2411.09484/) (2024)
- [Rethinking LoRA for Privacy-Preserving Federated Learning in Large Models](https://mlsanity.com/paper/2602.19926/) (2026)
- [Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding](https://mlsanity.com/paper/2512.14236/) (2025)
- [Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation](https://mlsanity.com/paper/2602.11743/) (2026)
- [RaCo: Ranking and Covariance for Practical Learned Keypoints](https://mlsanity.com/paper/2602.15755/) (2026)
- [Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison](https://mlsanity.com/paper/2502.20154/) (2025)
- [Metadata-free Georegistration of Ground and Airborne Imagery](https://mlsanity.com/paper/2503.04927/) (2025)
- [A Streamlined Attention-Based Network for Descriptor Extraction](https://mlsanity.com/paper/2601.13126/) (2026)
- [Consensus Learning with Deep Sets for Essential Matrix Estimation](https://mlsanity.com/paper/2406.17414/) (2024)
- [EdgePoint2: Compact Descriptors for Superior Efficiency and Accuracy](https://mlsanity.com/paper/2504.17280/) (2025)
- [Understanding and Optimizing Attention-Based Sparse Matching for Diverse Local Features](https://mlsanity.com/paper/2602.08430/) (2026)
- [BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation](https://mlsanity.com/paper/2603.05921/) (2026)
- [Deep Image Clustering Based on Curriculum Learning and Density Information](https://mlsanity.com/paper/2604.03306/) (2026)
- [Who Handles Orientation? Investigating Invariance in Feature Matching](https://mlsanity.com/paper/2604.11809/) (2026)
- [Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison](https://mlsanity.com/paper/2609.01530/) (2026)
- [CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation](https://mlsanity.com/paper/2601.09230/) (2026)
- [XRefine: Attention-Guided Keypoint Match Refinement](https://mlsanity.com/paper/2601.12530/) (2026)
- [Matching of SAR and optical images based on transformation to shared modality](https://mlsanity.com/paper/2602.12515/) (2026)
- [From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection](https://mlsanity.com/paper/2602.20630/) (2026)

## Abstract (arXiv)

In this paper, we analyze and improve into the recently proposed DeDoDe keypoint detector. We focus our analysis on some key issues. First, we find that DeDoDe keypoints tend to cluster together, which we fix by performing non-max suppression on the target distribution of the detector during training. Second, we address issues related to data augmentation. In particular, the DeDoDe detector is sensitive to large rotations. We fix this by including 90-degree rotations as well as horizontal flips. Finally, the decoupled nature of the DeDoDe detector makes evaluation of downstream usefulness problematic. We fix this by matching the keypoints with a pretrained dense matcher (RoMa) and evaluating two-view pose estimates. We find that the original long training is detrimental to performance, and therefore propose a much shorter training schedule. We integrate all these improvements into our proposed detector DeDoDe v2 and evaluate it with the original DeDoDe descriptor on the MegaDepth-1500 and IMC2022 benchmarks. Our proposed detector significantly increases pose estimation results, notably from 75.9 to 78.3 mAA on the IMC2022 challenge. Code and weights are available at https://github.com/Parskatt/DeDoDe