Library/Grounded-Segment-AnythingForked

IDEA-Research/Grounded-Segment-Anything

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

View on GitHub↗Upstream IDEA-Research/Grounded-Segment-Anything↗

Builder

IDEA-Research

IDEA-Research • individual

Stars

17,497

Using upstream star count

Forks

1,589

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Apr 6, 2023

Project creation date

README Summary

Grounded-Segment-Anything combines multiple AI models including Grounding DINO, Segment Anything Model (SAM), and Stable Diffusion to create a comprehensive computer vision pipeline. The project enables automatic detection, segmentation, and generation of objects in images through natural language prompts. It provides an integrated solution for various vision tasks including object detection, image segmentation, and image generation.

AI Dev Skills

Unmapped

Object DetectionInstance SegmentationOpen-vocabulary Vision ModelsVision TransformersGrounding DINO ArchitectureSegment Anything Model (SAM)Image Generation with Diffusion ModelsMultimodal Vision-Language ModelsModel Integration and EnsemblingComputer Vision Pipeline DesignTransfer LearningZero-shot Detection

Taxonomy

AI Trends

Multimodal Reasoning Foundation Models Open-vocabulary Vision Compound AI Systems Vision-Language Models Generative AI

Deployment Context

Self-hosted On-premise Cloud API

Industries

Robotics Autonomous Systems Content Creation Video Analysis Medical Imaging Quality Inspection

Modalities

Image Multimodal Video

Skill Areas

Object Detection Instance Segmentation Open-vocabulary Vision Models Vision Transformers Grounding DINO Architecture Segment Anything Model (SAM)Image Generation with Diffusion Models Multimodal Vision-Language Models Model Integration and Ensembling Computer Vision Pipeline Design Transfer Learning Zero-shot Detection

Use Cases

Automatic object detection and segmentation without predefined classes Image editing and object manipulation Scene understanding for robotics Video object tracking and segmentation Automated annotation and labeling Content-aware image generation Interactive object selection Visual relationship understanding

Recent Activity

Updated 1 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: high
Maturity: research

PM Skills

Developer Platform

Languages

Jupyter Notebook100.0%

Timeline

Project created: Apr 6, 2023
Forked: Mar 26, 2026
Your last push: 1 years ago
Upstream last push: 1 years ago
Tracked since: Sep 5, 2024

Similar Repos

pgvector cosine similarity · $0

Loading…