A Perspective-n-Points-and-Lines method.

Self-supervised vIsion Transformer (SiT)

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Joint deep network for feature line detection and description

Fast and robust certifiable relative pose estimation

center loss for face recognition

Pytorch Implementation of Unifying Deep Local and Global Features for Image Search (DELG)

Pytorch implementation of convolutional neural network visualization techniques

A curated list of Visual Place Recognition (VPR)/ loop closure detection (LCD) datasets

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

视觉(语义) SLAM 相关研究跟踪

End-to-end learning of deep visual representations for image retrieval

Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

My personal note about local and global descriptor

PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"

📝Awesome and classical image retrieval papers

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

Open source Structure-from-Motion pipeline

3D restruction algorithm

This repository contains the code for our papers "Learning Condition Invariant Features for Retrieval-Based Localization from 1M Images" and "Geometrically Mappable Image Features".

Implementation of CVPR'20 paper - ASLFeat: Learning Local Features of Accurate Shape and Localization

🏞 A content-based image retrieval (CBIR) system

深度学习面试宝典（含数学、机器学习、深度学习、计算机视觉、自然语言处理和SLAM等方向）

SNE-RoadSeg in PyTorch, ECCV 2020