Stars
🚀 Deep learning includes superpoint-superglue(C++, TensorRT), and traditional algorithms include zkaze, surf, ORB, etc.
Criss-Cross Attention (2d&3d) for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
Training library for local feature detection and matching
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
This is a toolbox repository to help evaluate various methods that perform image matching from a pair of images.
LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
A personal list of papers and resources of image matching and pose estimation, including perspective images and panoramas.
[SuperGlue: Learning Feature Matching with Graph Neural Networks] This repo includes PyTorch code for training the SuperGlue matching network on top of SIFT keypoints and descriptors.
Superpoint and Superglue training and testing code, also some traditional method (SIFT and ORB)
Some information about parameters and options available in COLMAP - SfM & MVS software. https://colmap.github.io
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
Pytorch Implementation of rpautrat/SuperPoint
Open Source Graph Neural Net Based Pipeline for Image Matching
Pose estimation pipeline for 3D Reconstruction using LoFTR (Local Feature Transformer) detector free feature matcher.
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task
QuadTree Attention for Vision Transformers (ICLR2022)
PyTorch implementation of a collections of scalable Video Transformer Benchmarks.
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints, IROS 2020
Efficient neural feature detector and descriptor
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
C++ library based on tensorrt integration
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking