Vision par ordinateur
supervision
roboflow/supervision
Reusable utilities for computer vision data handling, detection annotation and tracking workflows.
★ 49,9K⑂ 4,8KPython
ToolAI.io · Chaîne GitHub
Vision par ordinateur · Projets AI open source sur GitHub
Un index factuel des projets de développement LLM, agent, MCP, RAG et AI, avec pour chaque entrée la licence, la configuration, le téléchargement, des captures d’écran et les ressources associées.
Données du dépôt public
Index du projet
Vision par ordinateur
Segment Anything: Generate Image Segmentation Masks with Points and Boxes
facebookresearch/segment-anything
Meta’s SAM image segmentation project supports prompt inputs such as points and boxes, and can also automatically generate candidate masks for an entire image. It is suitable for interactive annotation and image processing workflows.
★ 54,8K⑂ 6,4KPython
Vision par ordinateur
DINOv2: visual features for classification and retrieval
facebookresearch/dinov2
Meta’s self-supervised vision models provide pretrained backbones and task heads for feature extraction, visual retrieval and downstream adaptation.
★ 13,3K⑂ 1,3KPython
Vision par ordinateur
GLM-OCR: document recognition with Markdown and JSON output
zai-org/GLM-OCR
An OCR project for tables, formulas and complex layouts, with hosted and self-hosted pipelines, a CLI and a Python SDK.
★ 7,5K⑂ 671Python
Vision par ordinateur
PaddleDetection
PaddlePaddle/PaddleDetection
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
★ 14,3K⑂ 3KPython
Vision par ordinateur
PaddleSeg
PaddlePaddle/PaddleSeg
Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.
★ 9,4K⑂ 1,7KPython
Vision par ordinateur
sam2
facebookresearch/sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
★ 19,6K⑂ 2,5KJupyter Notebook
Vision par ordinateur
VGGT: Estimating Cameras, Depth, and 3D Structure from Multi-View Images
facebookresearch/vggt
Visual Geometry Grounded Transformer predicts camera parameters, depth maps, point maps, and point tracks from scene images, making it suitable for preliminary geometric estimation in 3D vision research and reconstruction workflows.
★ 14,4K⑂ 1,5KPython
Page 2 / 2 · 20 projets