# DKM: Dense Kernelized Feature Matching for Geometry Estimation

arXiv: https://arxiv.org/abs/2202.00667 · HTML: https://mlsanity.com/paper/2202.00667/

## Key facts

- Cited by 177 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 60 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (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)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [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)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences](https://mlsanity.com/paper/1912.05524/) (2019)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [QuadTree Attention for Vision Transformers](https://mlsanity.com/paper/2201.02767/) (2022)
- [Learning a Discriminative Feature Network for Semantic Segmentation](https://mlsanity.com/paper/1804.09337/) (2018)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutions](https://mlsanity.com/paper/2004.10566/) (2020)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [DGC-Net: Dense Geometric Correspondence Network](https://mlsanity.com/paper/1810.08393/) (2018)
- [RANSAC-Flow: generic two-stage image alignment](https://mlsanity.com/paper/2004.01526/) (2020)
- [Large-scale, real-time visual-inertial localization revisited](https://mlsanity.com/paper/1907.00338/) (2019)
- [A Minimal Solution for Two-view Focal-length Estimation using Two Affine Correspondences](https://mlsanity.com/paper/1706.01649/) (2017)
- [Making Affine Correspondences Work in Camera Geometry Computation](https://mlsanity.com/paper/2007.10032/) (2020)
- [Minimal Solutions for Relative Pose with a Single Affine Correspondence](https://mlsanity.com/paper/1912.10776/) (2019)
- [On the Instability of Relative Pose Estimation and RANSAC's Role](https://mlsanity.com/paper/2112.14651/) (2021)

## Built on by (most cited first, 30 of 177)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (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)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [GlueStick: Robust Image Matching by Sticking Points and Lines Together](https://mlsanity.com/paper/2304.02008/) (2023)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [XoFTR: Cross-modal Feature Matching Transformer](https://mlsanity.com/paper/2404.09692/) (2024)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [CROSSFIRE: Camera Relocalization On Self-Supervised Features from an Implicit Representation](https://mlsanity.com/paper/2303.04869/) (2023)
- [FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction](https://mlsanity.com/paper/2412.09573/) (2024)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector](https://mlsanity.com/paper/2404.08928/) (2024)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)
- [UFM: A Simple Path towards Unified Dense Correspondence with Flow](https://mlsanity.com/paper/2506.09278/) (2025)
- [Tame a Wild Camera: In-the-Wild Monocular Camera Calibration](https://mlsanity.com/paper/2306.10988/) (2023)
- [GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects](https://mlsanity.com/paper/2403.11510/) (2024)
- [Cross-View Completion Models are Zero-shot Correspondence Estimators](https://mlsanity.com/paper/2412.09072/) (2024)
- [PMatch: Paired Masked Image Modeling for Dense Geometric Matching](https://mlsanity.com/paper/2303.17342/) (2023)
- [Local Feature Matching Using Deep Learning: A Survey](https://mlsanity.com/paper/2401.17592/) (2024)
- [GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyond](https://mlsanity.com/paper/2403.19632/) (2024)
- [Diffusion Model for Dense Matching](https://mlsanity.com/paper/2305.19094/) (2023)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis](https://mlsanity.com/paper/2411.03637/) (2024)
- [Relative Pose Estimation through Affine Corrections of Monocular Depth Priors](https://mlsanity.com/paper/2501.05446/) (2025)

## Abstract (arXiv)

Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find all correspondences. Perhaps counter-intuitively, dense methods have previously shown inferior performance to their sparse and semi-sparse counterparts for estimation of two-view geometry. This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation. The novelty is threefold: First, we propose a kernel regression global matcher. Secondly, we propose warp refinement through stacked feature maps and depthwise convolution kernels. Thirdly, we propose learning dense confidence through consistent depth and a balanced sampling approach for dense confidence maps. Through extensive experiments we confirm that our proposed dense method, Dense Kernelized Feature Matching, sets a new state-of-the-art on multiple geometry estimation benchmarks. In particular, we achieve an improvement on MegaDepth-1500 of +4.9 and +8.9 AUC@5circ compared to the best previous sparse method and dense method respectively. Our code is provided at https://github.com/Parskatt/dkm