# RoMa: Robust Dense Feature Matching

arXiv: https://arxiv.org/abs/2305.15404 · HTML: https://mlsanity.com/paper/2305.15404/

## Key facts

- Cited by 302 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 69 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [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)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [Prior Guided Feature Enrichment Network for Few-Shot Segmentation](https://mlsanity.com/paper/2008.01449/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Neighbourhood Consensus Networks](https://mlsanity.com/paper/1810.10510/) (2018)
- [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)
- [Revealing the Dark Secrets of Masked Image Modeling](https://mlsanity.com/paper/2205.13543/) (2022)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Hierarchical Scene Coordinate Classification and Regression for Visual Localization](https://mlsanity.com/paper/1909.06216/) (2019)
- [Dual-Resolution Correspondence Networks](https://mlsanity.com/paper/2006.08844/) (2020)

## Built on by (most cited first, 30 of 302)

- [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)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [Aether: Geometric-Aware Unified World Modeling](https://mlsanity.com/paper/2503.18945/) (2025)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment](https://mlsanity.com/paper/2412.16334/) (2024)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting](https://mlsanity.com/paper/2410.22128/) (2024)
- [FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2506.05348/) (2025)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [Light3R-SfM: Towards Feed-forward Structure-from-Motion](https://mlsanity.com/paper/2501.14914/) (2025)
- [SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting](https://mlsanity.com/paper/2411.17190/) (2024)
- [FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction](https://mlsanity.com/paper/2412.09573/) (2024)
- [No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views](https://mlsanity.com/paper/2508.01171/) (2025)
- [DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector](https://mlsanity.com/paper/2404.08928/) (2024)
- [CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents](https://mlsanity.com/paper/2407.01511/) (2024)
- [AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis](https://mlsanity.com/paper/2504.13157/) (2025)
- [YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting](https://mlsanity.com/paper/2511.07321/) (2025)
- [UFM: A Simple Path towards Unified Dense Correspondence with Flow](https://mlsanity.com/paper/2506.09278/) (2025)
- [MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing](https://mlsanity.com/paper/2408.08000/) (2024)
- [Cross-View Completion Models are Zero-shot Correspondence Estimators](https://mlsanity.com/paper/2412.09072/) (2024)
- [MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion](https://mlsanity.com/paper/2504.20040/) (2025)
- [Emergent Outlier View Rejection in Visual Geometry Grounded Transformers](https://mlsanity.com/paper/2512.04012/) (2025)
- [C3G: Learning Compact 3D Representations with 2K Gaussians](https://mlsanity.com/paper/2512.04021/) (2025)
- [iLRM: An Iterative Large 3D Reconstruction Model](https://mlsanity.com/paper/2507.23277/) (2025)
- [FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training](https://mlsanity.com/paper/2411.02229/) (2024)
- [Relative Pose Estimation through Affine Corrections of Monocular Depth Priors](https://mlsanity.com/paper/2501.05446/) (2025)
- [Cluster and Predict Latent Patches for Improved Masked Image Modeling](https://mlsanity.com/paper/2502.08769/) (2025)

## Abstract (arXiv)

Feature matching is an important computer vision task that involves estimating correspondences between two images of a 3D scene, and dense methods estimate all such correspondences. The aim is to learn a robust model, i.e., a model able to match under challenging real-world changes. In this work, we propose such a model, leveraging frozen pretrained features from the foundation model DINOv2. Although these features are significantly more robust than local features trained from scratch, they are inherently coarse. We therefore combine them with specialized ConvNet fine features, creating a precisely localizable feature pyramid. To further improve robustness, we propose a tailored transformer match decoder that predicts anchor probabilities, which enables it to express multimodality. Finally, we propose an improved loss formulation through regression-by-classification with subsequent robust regression. We conduct a comprehensive set of experiments that show that our method, RoMa, achieves significant gains, setting a new state-of-the-art. In particular, we achieve a 36% improvement on the extremely challenging WxBS benchmark. Code is provided at https://github.com/Parskatt/RoMa