# RoMa v2: Harder Better Faster Denser Feature Matching

arXiv: https://arxiv.org/abs/2511.15706 · HTML: https://mlsanity.com/paper/2511.15706/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 63 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 30 of 47)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [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)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Virtual KITTI 2](https://mlsanity.com/paper/2001.10773/) (2020)
- [Virtual Worlds as Proxy for Multi-Object Tracking Analysis](https://mlsanity.com/paper/1605.06457/) (2016)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [A General and Adaptive Robust Loss Function](https://mlsanity.com/paper/1701.03077/) (2017)
- [DKM: Dense Kernelized Feature Matching for Geometry Estimation](https://mlsanity.com/paper/2202.00667/) (2022)
- [Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow](https://mlsanity.com/paper/1802.07095/) (2018)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)

## Built on by (most cited first, 30 of 51)

- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [World Reconstruction From Inconsistent Views](https://mlsanity.com/paper/2603.16736/) (2026)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [Glob3R: Global Structure-from-Motion with 3D Foundation Models](https://mlsanity.com/paper/2607.09225/) (2026)
- [StreamTTO: Efficient Online Test-Time Optimization for Video Depth Completion](https://mlsanity.com/paper/2603.01765/) (2026)
- [GGPT: Geometry Grounded Point Transformer](https://mlsanity.com/paper/2603.11174/) (2026)
- [TerraSky3D: Multi-View Reconstructions of European Landmarks in 4K](https://mlsanity.com/paper/2603.28287/) (2026)
- [Are Pretrained Image Matchers Good Enough for SAR-Optical Satellite Registration?](https://mlsanity.com/paper/2604.10217/) (2026)
- [VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion](https://mlsanity.com/paper/2607.27194/) (2026)
- [CM-Bench: A Comprehensive Cross-Modal Feature Matching Benchmark Bridging Visible and Infrared Images](https://mlsanity.com/paper/2603.12690/) (2026)
- [PiLoT: Neural Pixel-to-3D Registration for UAV-based Ego and Target Geo-localization](https://mlsanity.com/paper/2603.20778/) (2026)
- [Who Handles Orientation? Investigating Invariance in Feature Matching](https://mlsanity.com/paper/2604.11809/) (2026)
- [Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives](https://mlsanity.com/paper/2606.04788/) (2026)
- [G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation](https://mlsanity.com/paper/2606.08284/) (2026)
- [OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos](https://mlsanity.com/paper/2606.25245/) (2026)
- [Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparison](https://mlsanity.com/paper/2609.01530/) (2026)
- [IUP-Pose: Decoupled Iterative Uncertainty Propagation for Real-time Relative Pose Regression via Implicit Dense Alignment v1](https://mlsanity.com/paper/2603.19625/) (2026)
- [Drive-Through 3D Vehicle Exterior Reconstruction via Dynamic-Scene SfM and Distortion-Aware Gaussian Splatting](https://mlsanity.com/paper/2603.26638/) (2026)
- [Privacy-Preserving Structureless Visual Localization via Image Obfuscation](https://mlsanity.com/paper/2604.12068/) (2026)
- [FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles](https://mlsanity.com/paper/2605.03337/) (2026)
- [SG2Loc: Sequential Visual Localization on 3D Scene Graphs](https://mlsanity.com/paper/2606.11880/) (2026)
- [REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching](https://mlsanity.com/paper/2606.24330/) (2026)
- [Dynamic Inverse Rendering for Enhanced Material-Lighting Decomposition](https://mlsanity.com/paper/2607.09329/) (2026)
- [DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion](https://mlsanity.com/paper/2607.09507/) (2026)
- [FillGS: Filling Observation Gaps in 4D Gaussian Splatting via Viewpoint-Time Selection and Generative Refinement](https://mlsanity.com/paper/2607.29284/) (2026)
- [LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching](https://mlsanity.com/paper/2608.04106/) (2026)
- [Promptable Animal Pose Tracking Across Species](https://mlsanity.com/paper/2608.04995/) (2026)
- [Semi-Dense Matching Uncertainty Is Not Just Local Confidence](https://mlsanity.com/paper/2608.08685/) (2026)
- [NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge](https://mlsanity.com/paper/2608.09782/) (2026)
- [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026)

## Abstract (arXiv)

Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold standard due to its high accuracy and robustness. However, existing dense matchers still fail or perform poorly for many hard real-world scenarios, and high-precision models are often slow, limiting their applicability. In this paper, we attack these weaknesses on a wide front through a series of systematic improvements that together yield a significantly better model. In particular, we construct a novel matching architecture and loss, which, combined with a curated diverse training distribution, enables our model to solve many complex matching tasks. We further make training faster through a decoupled two-stage matching-then-refinement pipeline, and at the same time, significantly reduce refinement memory usage through a custom CUDA kernel. Finally, we leverage the recent DINOv3 foundation model along with multiple other insights to make the model more robust and unbiased. In our extensive set of experiments, we show that the resulting novel matcher sets a new state-of-the-art, being significantly more accurate than its predecessors. Code is available at https://github.com/Parskatt/romav2