检测 / 分割

Emgu CV is a cross platform .Net wrapper to the OpenCV image processing library.

Add object detection, tracking, mobile notifications, and search to any security camera.

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

An open source library and framework for deep learning on satellite and aerial imagery.

A ComfyUI custom node designed for advanced image background removal and object, face, clothes, and fashion segmentation, utilizing multiple models including RMBG-2.0, VRMBG-3.0, FeyNoBg, Finegrain Box Segmenter, INSPYRENET, BEN, BEN2, BiRefNet, Lucida, SDMatte, SAM, SAM2, SAM3, Florence-2, YOLOv8/YOLO11, Big-Lama, and GroundingDINO.

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

[DEIMv2] Real Time Object Detection Meets DINOv3

NVIDIA DeepStream SDK 8.0 / 7.1 / 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

CVNets: A library for training computer vision networks

A modern, web-based photo management server. Run it on your home server and it will let you find the right photo from your collection on any device. Smart filtering is made possible by object recognition, face recognition, location awareness, color analysis and other ML algorithms.

Learn autonomous driving by building it: Python simulations and an open textbook where the system grows one stage at a time. Swap and compare localization, planning and control algorithms in the same system.

🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️

Core ML model zoo for iOS/macOS — PyTorch models converted to ready-to-use .mlpackage, each with a conversion script and SwiftUI sample app. Sibling repos cover Apple's Core AI framework (iOS/macOS 27) and on-device LLMs.

Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.

TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet

Vocal Remover using Deep Neural Networks

Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".

[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆28 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

[CVPR2026] Detect Anything via Next Point Prediction

PyTorch extensions for fast R&D prototyping and Kaggle farming

"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023 Top-10 Cited 🏆) & (NTIRE 2024 Runner-Up 🏆) & (NTIRE 2025 Winner 🏆) & (NTIRE 2026 Winner 🏆)

[ICLR 2023 Spotlight] Vision Transformer Adapter for Dense Predictions

Yolov5 deepsort inference，使用YOLOv5+Deepsort实现车辆行人追踪和计数，代码封装成一个Detector类，更容易嵌入到自己的项目中

🔥🔥🔥TensorRT for YOLO26 (det/pose/seg/depth/obb/cls), YOLOv11,YOLOv10 YOLOv9,YOLOv8, ... 🚀🚀🚀 CUDA IS ALL YOU NEED. 🍎🍎🍎

OpenCV-Python4.1 中文文档

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

Real-time and accurate open-vocabulary end-to-end object detection

Build, train, optimize, and run computer vision models locally, from raw images to live inference. Open source, optimized for Intel® XPU (CUDA also supported).

Using Diffusion Models to Segment/Reconstruct Organs from Medical Images [AAAI Most influential Paper]

Frigate integration for Home Assistant

Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]

StarDist - Object Detection with Star-convex Shapes

Replication of simple CV Projects including attention, classification, detection, keypoint detection, etc.

🧬 High-performance TensorFlow Lite library for React Native with GPU acceleration

Legacy JSON-to-YOLO dataset converter for COCO, LabelMe, Labelbox, VoTT, INFOLKS, and ATH annotations. Superseded by convert_coco() in the Ultralytics package.

Intel / AMD CPU Internals

🌝 MLKit是一个强大易用的工具包。通过ML Kit您可以很轻松的实现文字识别、条码识别、图像标记、人脸检测、对象检测等功能。

Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.

Cornerstone is a set of JavaScript libraries that can be used to build web-based medical imaging applications. It provides a framework to build radiology applications such as the OHIF Viewer.

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Ultralytics YOLOv8, YOLOv9, YOLOv10, YOLOv11, YOLOv12 for ROS 2

The modern, local-first platform for professional video surveillance.

A lean C++ library for working with point cloud data

Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

Microsoft AI for Good Lab — Biodiversity research hub. Open-source AI models, edge devices, and tools for biodiversity monitoring and conservation. Your source for MegaDetector, SPARROW, PytorchWildlife, Bioacoustics, and more.

Python framework that facilitates the quick development of complex video analysis applications and other series-processing based applications in a multiprocessing environment.

A Japanese Tokenizer for Business

LibreYOLO is a MIT licensed open source computer vision library