image-retrieval 开源项目推荐（772 个）

KevinMusgrave /pytorch-metric-learning

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

soruly /trace.moe

无处不在的动漫剪辑的时间戳检索

KaiyangZhou /deep-person-reid

Torchreid: Deep learning person re-identification in PyTorch.

layumi /Person_reID_baseline_pytorch

:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

cvg /Hierarchical-Localization

使用hloc轻松实现视觉定位

JDAI-CV /fast-reid

SOTA重新识别方法和任务

towhee-io /towhee

Towhee 是一个致力于让神经数据处理流水线变得简单且快速的框架。

InternLM /HuixiangDou

汇翔斗：通过法学硕士技术援助克服群聊场景

willard-yuan /awesome-cbir-papers

📝Awesome and classical image retrieval papers

filipradenovic /cnnimageretrieval-pytorch

CNN Image Retrieval in PyTorch: Training and evaluating CNNs for Image Retrieval in PyTorch

NVlabs /DG-Net

：夫妇：联合区分性和生成性学习用于人重新认同。CVPR ' 19（口头）：夫妇：

PyRetri /PyRetri

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

Vincentqyw /Recent-Stars-2025

🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

wuji3 /Doraemon

A powerful baseline for image classification, face recognition and image retrieval with Pytorch

TurtleZhong /Map-based-Visual-Localization

A general framework for map-based visual localization. It contains 1) Map Generation which support traditional features or deeplearning features. 2) Hierarchical-Localizationvisual in visual(points or line) map. 3)Fusion framework with IMU, wheel odom and GPS sensors.

dermotte /LIRE

Open source library for content based image retrieval / visual information retrieval.

matsui528 /sis

Simple image search engine

bnu-wangxun /Deep_Metric

Deep Metric Learning

TIGER-AI-Lab /VLM2Vec

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

layumi /University1652-Baseline

ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.