Vincentqyw / RoMa
[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
☆13Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for RoMa
- ONNX-compatible OmniGlue: Generalizable Feature Matching with Foundation Model Guidance☆21Updated 5 months ago
- Light-weight library to perform homography estimation with RANSAC from point, line or point-line correspondences☆43Updated last year
- Official code of ResMatch: Residual Attention Learning for Local Feature Matching☆34Updated last year
- Pytorch implementation of ConvMatch for AAAI'23 paper "ConvMatch: Rethinking Network Design for Two-View Correspondence Learning"☆25Updated 5 months ago
- Paper has been accepted by CVPR2023, focus on image matching.☆37Updated last year
- ☆38Updated 2 years ago
- Official implementation of Semantic SuperPoint (LARS-2022): https://arxiv.org/abs/2211.01098☆41Updated last year
- ☆65Updated last year
- [CVPR 2022] Efficient Large-scale Localization by Global Instance Recognition. Performing large-scale localization from global instances …☆17Updated last year
- ☆31Updated last year
- Implementation of ECCV 2020 paper "Geometric Estimation via Robust Subspace Recovery" and IEEE TPAMI 2021 paper "Efficient Deterministic …☆18Updated 3 years ago
- Shared Coupling-bridge for Weakly Supervised Local Feature Learning☆22Updated last year
- VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition (ECCV 2024)☆32Updated 3 weeks ago
- ☆30Updated 3 months ago
- ☆16Updated 2 years ago
- ☆31Updated 3 years ago
- [ECCV workshop 2024] Visual localization with NeRFs☆25Updated 2 months ago
- ☆12Updated last year
- converts image matches to COLMAP format☆26Updated last month
- SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)☆13Updated 2 months ago
- Evaluation of Line Detection and Association☆49Updated last year
- 2D-3D Matching☆28Updated 3 years ago
- ☆26Updated last year
- ☆37Updated 11 months ago
- DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing☆46Updated last month
- C++-compatible fork of SuperGlue☆29Updated 4 years ago
- ☆86Updated last year
- Code for CVPR2023 paper:Adaptive Assignment for Geometry Aware Local Feature Matching☆99Updated last year
- ☆30Updated 8 months ago
- An unsupervised interest point detection and description method named Properties Optimization Point (POP)☆8Updated 3 years ago