检测 / 分割

一个包覆盖检测/分割/姿态/跟踪全流程，替代自建训练脚本和分散的模型仓库

PyTorch 生态里最省事的检测/分割基线，用来快速验证数据和导出部署模型

本地跑的 NVR，用 AI 加速器做实时目标检测，替代云端订阅式摄像头服务

PyTorch 图像骨干网络与预训练权重的统一入口，顶替散落各处的各模型官方实现

在 PyTorch 上搭检测/分割训练流水线时，用它顶替自己写 backbone、RPN、ROI head 和分布式训练脚手架

PyTorch 检测/分割的模块化基座，用来替换自己手写的 backbone-neck-head 胶水代码

人脸检测与识别模型的事实标准实现，替换掉自研 RetinaFace/ArcFace 训练管线

按网络逐个讲透结构并给可跑实现的图像处理教程仓库，用来替代零散博客和论文复现

一个文件一个 ViT 变体的参考实现库，用来读论文代码和搭实验骨架，不是拿来直接上线的模型库

Meta 的可提示图像/视频分割基础模型，顶替掉你手写的跟踪+分割流水线

统一处理图像、掩码、框和关键点的增强层，替换掉自己手写的 torchvision transforms 拼装

飞桨系的目标检测全家桶，从训练到多硬件部署一条链，替代 MMDetection 加自建部署脚本的组合

PyTorch 视觉模型的可解释性工具包，用 CAM 热力图替换掉自己手写 hook 抓激活的那套脚本

桌面端多模态标注工具，用内置模型预标注替代 Labelme 加一堆脚本拼起来的流程

表格和时间序列任务上自动搜模型并堆集成，替掉手写调参和模型选型那一层

无锚框 YOLO 检测器，用一套训练代码同时覆盖科研复现和 TensorRT/ncnn 边缘部署

在 PyTorch 里训练和导出 YOLOv3 系列模型的参考实现，顶替 Darknet 原始仓库那条工具链

开源多模态对话模型家族，用一套权重同时覆盖单卡小模型和接近闭源旗舰的对话能力

用 DINOv2 骨干做实时检测/分割，微调后精度接近大模型但延迟留在 T4 实时区间

Roboflow 官方的 CV 模型上手 Notebook 集，用来在选型阶段快速验证某个 SOTA 模型能不能跑通

把任意 2D/3D 医学影像数据集自动配置成 U-Net 训练流水线的分割基线框架

把检测器输出接成轨迹的中间层，替换你手写的 SORT 或各仓库散落的跟踪脚本

Remove backgrounds from images directly in the browser environment with ease and no additional costs or privacy concerns. Explore an interactive demo.

All-in-One Development Tool based on PaddlePaddle

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Framework agnostic sliced/tiled inference + interactive ui + error analysis plots

computer vision and sports

Most popular metrics used to evaluate object detection algorithms.

unet for image segmentation

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.

A collection of sample apps to demonstrate how to use Google's ML Kit APIs on Android and iOS

Segment Anything in High Quality [NeurIPS 2023]

A Python package for segmenting geospatial data with the Segment Anything Model (SAM)

Self-hosted, local only NVR and AI Computer Vision software. With features such as object detection, motion detection, face recognition and more, it gives you the power to keep an eye on your home, office or any other place you want to monitor.

GeoAI: Artificial Intelligence for Geospatial Data

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Accelerated deep learning R&D

Efficient vision foundation models for high-resolution generation and perception.

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.

A cross-platform video structuring (video analysis) framework based on CV models & mLLM.

ICCV 2025 论文和开源项目合集

Images to inference with no labeling (use foundation models to train supervised models).

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Pytorch framework for doing deep learning on point clouds.

[IEEE TMI Best Paper Award] Official Implementation for UNet++

Deep Learning Server and CLI for Torch and TensorRT

Collection of papers, datasets, code and other resources for object tracking and detection using deep learning

Lightweight nudity detection

a generalist algorithm for cellular segmentation with human-in-the-loop capabilities

detrex is a research platform for DETR-based object detection, segmentation, pose estimation and other visual recognition tasks.