[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.
-
Updated
Jun 3, 2024 - Python
[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.
Code to easily try 23 (and growing) different image matching methods
Patch2Pix: Epipolar-Guided Pixel-Level Correspondences [CVPR2021]
Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021, T-PAMI 2022
🤗 image matching toolbox webui
Image Feature Matching with Julia using freak descriptor
Make Rendered Database using Rendered Image Obtained by Trained Gaussian Splatting
ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO
Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)
[AAAI2023] TopicFM: Robust, Efficient, and Interpretable Topic-Assisted Feature Matching
[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
A C++ SIFT implementation (Scale invariant feature transform)
SuperPoint and SuperGlue with TensorRT. Deploy with C++.
Visual localization made easy with hloc
Conversion of depth data to derived images that allow classical feature detection. My master thesis.
A framework for building high-performance real-time multiple object trackers
This reposetory contains codes to evaluate the extent of attenuation of shock waves.
Product recognition on store shelves with Computer Vision tecniques (university project for Computer Vision and Image Processing)
[TITS] reliable dense matching based point cloud registration for autonomous driving
Implementation of my MSc thesis work, entitled "Optical pose estimation in robotics applications"
Add a description, image, and links to the feature-matching topic page so that developers can more easily learn about it.
To associate your repository with the feature-matching topic, visit your repo's landing page and select "manage topics."