Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Detection, segmentation, tracking, OCR models, 3D reconstruction and classical vision.
Signals: computer-vision, object-detection, image-segmentation, yolo, opencv, image-classification, pose-estimation, object-tracking
1,478 results
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
Awesome Crowd Counting
A Python package for fast and robust Image Stitching
computer vision projects | 计算机视觉相关好玩的AI项目（Python、C++、embedded system）
The Open Source Framework for Machine Vision
Images to inference with no labeling (use foundation models to train supervised models).
[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
ICCV 2025 论文和开源项目合集
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.
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet
FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)
Awesome work on hand pose estimation/tracking
3D Computer Vision Framework
Visual tracking library based on PyTorch.
Free to use online tool for labelling photos. https://makesense.ai
[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
repository to research & share the machine learning articles
A curated list of papers & resources linked to 3D reconstruction from images.
:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"
A large scale non-linear optimization library
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
24,523 repositories in the index in total.
