There are 2 repositories under superpoint topic.
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
đ¤ image matching toolbox webui
Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"
small c++ library to quickly deploy models using onnxruntime
ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO
đ Deep learning includes superpoint-superglue(C++, TensorRT), and traditional algorithms include zkaze, surf, ORB, etc.
SuperPoint and SuperGlue with TensorRT. Deploy with C++.
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
Integrate SuperPoint and LightGlue into OpenCV image stitching or Matching algorithm
Benchmarking and evaluation framework for place recognition methods, featuring SuperPoint+SuperGlue, LoGG3D-Net, Scan Context, DBoW2, MixVPR, STD
SuperSLAM: Open Source Framework for Deep Learning based Visual SLAM (Work in Progress)
ROS wrapper for SuperGlue and SuperPoint models
Using SuperGlue (from Magic Leap team) in Visual Place Recognition tasks. Providing full workflow from videos/images to end-to-end API and step-by-step how to use all codes.
C++ implementation of SuperPoint inference in LibTorch
Graph based SLAM for multiple cameras using SuperPoint feature detector
Image features and related matching methods
Deployment and evaluation code for a SuperPoint-based Stereo Visual Odometry
CVPR 2022 "Image Matching: Local Features and Beyond" workshop challenge: Kaggle Silver Medal solution (34th out of 642 teams).
SuperPoint with pretrain model and implement in Pytorch C++
Pytorch implemenation of structure from motion using Libviso2, SIFT, SuperPoint, SPyNet and Sfm Learner.
The implementation about feature matching using various method !!
Dive into cutting-edge FusionSLAM, where SuperPoint, SuperGlue, Neural Depth Estimation, and Instant-NGP converge, elevating Monocular SLAM to unparalleled precision and performance. Redefining mapping, localization, and reconstruction in a single camera setup.
Sparse-Dense Motion Modelling and Tracking for Manipulation without Prior Object Models
Twilight SLAM is unique framework augmenting the SLAM navigation frameworks with low-light image enhancement modules for navigating in dusky or extremely low-light or any illumination rendered featureless environments.
Building a full Visual SLAM pipeline to experiment with different techniques
Merge superpointălightglueăMixVPR into VINS-FUSION for loop closure with TensorRT
SuperPoint with pretrain model and implement in Tensorflow C++
App for comparing traditional and learned techniques of feature detection and description on Android
simple library to make life easy when deploying superpoint, superglue models