UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (NeurIPS 2025)
☆363Oct 15, 2026Updated last month
Alternatives and similar repositories for UFM
Users that are interested in UFM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆782Aug 30, 2026Updated 2 months ago
- Official implementation of our ICCV'25 paper "Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space"☆72May 23, 2026Updated 5 months ago
- [ECCV 2026 Oral] LoMa: Local Feature Matching Revisited☆499Updated this week
- MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)☆543Jul 9, 2025Updated last year
- [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and rel…☆1,341Jan 23, 2026Updated 9 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICCV 2025] Keypoint detection and description learned from image pairs only - no depth, no pose, no artificial augmentation required.☆125Aug 20, 2026Updated 3 months ago
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,272Updated this week
- A fast and simple structure from motion pipeline written in Pytorch.☆293Mar 13, 2026Updated 8 months ago
- [CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affin…☆241Apr 8, 2025Updated last year
- [CVPR26] MuM's a pretty good feature extractor for 3D tasks, probably the best.☆129Jul 14, 2026Updated 4 months ago
- MapAnything: Universal Feed-Forward Metric 3D Reconstruction☆3,921Aug 7, 2026Updated 3 months ago
- Code for "Multi-view Reconstruction via SfM-guided Monocular Depth Estimation". CVPR 2025 (Oral Presentation)☆390Sep 15, 2026Updated 2 months ago
- [CVPR 2026 Highlight] MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction☆45Jun 1, 2026Updated 5 months ago
- Implementation of RDD (CVPR 2025).☆129Jun 15, 2026Updated 5 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Generalizable Perception Stack for all things 3D, 4D & Scene Understanding☆100Mar 22, 2026Updated 7 months ago
- DaD's a pretty good keypoint detector, probably the best.☆115Oct 12, 2026Updated last month
- Cameras as Relative Positional Encoding☆773Dec 18, 2025Updated 11 months ago
- Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)☆309May 7, 2025Updated last year
- [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy☆1,013Feb 27, 2026Updated 8 months ago
- [ICLR2026] Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"☆405May 14, 2026Updated 6 months ago
- Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"☆452Nov 24, 2025Updated 11 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆3,171Nov 14, 2026Updated last week
- [ECCVW 2026] RoMa-Ω: What Feed-Forward 3D Models Know About Image Matching☆72Sep 10, 2026Updated 2 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆248Jul 16, 2025Updated last year
- Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"☆1,372Jan 5, 2026Updated 10 months ago
- [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"☆500Sep 19, 2025Updated last year
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆996Oct 27, 2025Updated last year
- ☆347Jun 30, 2026Updated 4 months ago
- [CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend☆516Jun 5, 2026Updated 5 months ago
- [CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences☆592Dec 2, 2024Updated last year
- Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features☆110Apr 8, 2025Updated last year
- Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views☆732May 1, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,217Nov 5, 2026Updated 2 weeks ago
- ☆540Sep 2, 2025Updated last year
- [CVPR 2025] AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis☆200Sep 5, 2025Updated last year
- Good Keypoints for the Two-View Geometry Estimation Problem. The reference implementation of the preprint.☆16May 30, 2025Updated last year
- [CVPR 26] Release repo of our work "Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers"☆200May 18, 2026Updated 6 months ago
- [CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training☆516Jun 11, 2026Updated 5 months ago
- AllTracker is a model for tracking all pixels in a video.☆439May 8, 2026Updated 6 months ago
Are these results useful?