# UFM: A Simple Path towards Unified Dense Correspondence with Flow

arXiv: https://arxiv.org/abs/2506.09278 · HTML: https://mlsanity.com/paper/2506.09278/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 79 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 30 of 63)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [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)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [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)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [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)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [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)
- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)

## Built on by (most cited first, 30 of 36)

- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [Any4D: Unified Feed-Forward Metric 4D Reconstruction](https://mlsanity.com/paper/2512.10935/) (2025)
- [E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training](https://mlsanity.com/paper/2512.10950/) (2025)
- [In Pursuit of Pixel Supervision for Visual Pre-training](https://mlsanity.com/paper/2512.15715/) (2025)
- [LoMa: Local Feature Matching Revisited](https://mlsanity.com/paper/2604.04931/) (2026)
- [PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis](https://mlsanity.com/paper/2508.13911/) (2025)
- [Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning](https://mlsanity.com/paper/2602.20157/) (2026)
- [MuM: Multi-View Masked Image Modeling for 3D Vision](https://mlsanity.com/paper/2511.17309/) (2025)
- [MegaFlow: Zero-Shot Large Displacement Optical Flow](https://mlsanity.com/paper/2603.25739/) (2026)
- [Cambrian-P: Pose-Grounded Video Understanding](https://mlsanity.com/paper/2605.22819/) (2026)
- [GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure](https://mlsanity.com/paper/2512.22274/) (2025)
- [GGPT: Geometry Grounded Point Transformer](https://mlsanity.com/paper/2603.11174/) (2026)
- [RadarGen: Automotive Radar Point Cloud Generation from Cameras](https://mlsanity.com/paper/2512.17897/) (2025)
- [Unified 3D Scene Understanding Through Physical World Modeling](https://mlsanity.com/paper/2605.24321/) (2026)
- [VLM3: Vision Language Models Are Native 3D Learners](https://mlsanity.com/paper/2605.30561/) (2026)
- [Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos](https://mlsanity.com/paper/2603.12064/) (2026)
- [Who Handles Orientation? Investigating Invariance in Feature Matching](https://mlsanity.com/paper/2604.11809/) (2026)
- [TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention](https://mlsanity.com/paper/2605.14315/) (2026)
- [OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos](https://mlsanity.com/paper/2606.25245/) (2026)
- [RayTun3R: Online Camera Adaptation in 3D Foundation Models](https://mlsanity.com/paper/2607.02711/) (2026)
- [CRISP: Contact-Guided Real2Sim from Monocular Video with Planar Scene Primitives](https://mlsanity.com/paper/2512.14696/) (2025)
- [FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles](https://mlsanity.com/paper/2605.03337/) (2026)
- [REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching](https://mlsanity.com/paper/2606.24330/) (2026)
- [Perceptual 3D Simulation With Physical World Modeling](https://mlsanity.com/paper/2606.27575/) (2026)
- [DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion](https://mlsanity.com/paper/2607.09507/) (2026)
- [MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors](https://mlsanity.com/paper/2607.12000/) (2026)
- [PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops](https://mlsanity.com/paper/2607.12811/) (2026)
- [LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching](https://mlsanity.com/paper/2608.04106/) (2026)
- [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026)

## Abstract (arXiv)

Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios and optical flow estimation, despite the common goal of matching content between two images. In this paper, we develop a Unified Flow & Matching model (UFM), which is trained on unified data for pixels that are co-visible in both source and target images. UFM uses a simple, generic transformer architecture that directly regresses the (u,v) flow. It is easier to train and more accurate for large flows compared to the typical coarse-to-fine cost volumes in prior work. UFM is 28% more accurate than state-of-the-art flow methods (Unimatch), while also having 62% less error and 6.7x faster than dense wide-baseline matchers (RoMa). UFM is the first to demonstrate that unified training can outperform specialized approaches across both domains. This result enables fast, general-purpose correspondence and opens new directions for multi-modal, long-range, and real-time correspondence tasks.