# S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching

arXiv: https://arxiv.org/abs/2004.01673 · HTML: https://mlsanity.com/paper/2004.01673/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [FoundPose: Unseen Object Pose Estimation with Foundation Features](https://mlsanity.com/paper/2311.18809/) (2023)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [Is Geometry Enough for Matching in Visual Localization?](https://mlsanity.com/paper/2203.12979/) (2022)
- [Progressive Correspondence Pruning by Consensus Learning](https://mlsanity.com/paper/2101.00591/) (2021)
- [Robust Incremental Structure-from-Motion with Hybrid Features](https://mlsanity.com/paper/2409.19811/) (2024)
- [SFD2: Semantic-guided Feature Detection and Description](https://mlsanity.com/paper/2304.14845/) (2023)
- [Guide Local Feature Matching by Overlap Estimation](https://mlsanity.com/paper/2202.09050/) (2022)
- [PNeRFLoc: Visual Localization with Point-based Neural Radiance Fields](https://mlsanity.com/paper/2312.10649/) (2023)
- [RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching](https://mlsanity.com/paper/2103.08573/) (2021)
- [Dense-SfM: Structure from Motion with Dense Consistent Matching](https://mlsanity.com/paper/2501.14277/) (2025)
- [Multi-sensor large-scale dataset for multi-view 3D reconstruction](https://mlsanity.com/paper/2203.06111/) (2022)
- [Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares](https://mlsanity.com/paper/2305.09527/) (2023)
- [Long-term Visual Localization with Mobile Sensors](https://mlsanity.com/paper/2304.07691/) (2023)
- [LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment](https://mlsanity.com/paper/2410.12269/) (2024)
- [ScaleNet: A Shallow Architecture for Scale Estimation](https://mlsanity.com/paper/2112.04846/) (2021)
- [MATCHA:Towards Matching Anything](https://mlsanity.com/paper/2501.14945/) (2025)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [RaCo: Ranking and Covariance for Practical Learned Keypoints](https://mlsanity.com/paper/2602.15755/) (2026)
- [MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction](https://mlsanity.com/paper/2603.27542/) (2026)
- [S2ML: Spatio-Spectral Mutual Learning for Depth Completion](https://mlsanity.com/paper/2511.06033/) (2025)
- [Efficient 3D Content Reconstruction and Generation](https://mlsanity.com/paper/2605.18052/) (2026)

## Abstract (arXiv)

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.