🎯 Awesome SAM Foundation Models

Comprehensive Resource Collection for Segment Anything

[](http://makeapullrequest.com) [](https://github.com/umitkacar/SAM-Foundation-Models)

🚀 Curated collection of SAM resources, implementations, optimizations & applications

Updated with 2024-2025 SOTA developments

---

📖 Explore • 🔥 Latest Updates • 💡 Applications • 🛠️ Tools • 📚 Learn

---

🚀 Production-Ready Repository

✅ Quality Assurance 96.55% Code Coverage - Comprehensive testing 100+ Linting Rules - Ruff fast linter Strict Type Checking - MyPy validation Pre-commit Hooks - Automated quality checks Security Auditing - UV vulnerability scanning Parallel Testing - pytest-xdist (16 workers)

🛠️ Modern Development Stack Build System: Hatch (PEP 621 compliant) Linting: Ruff (10-100x faster than flake8) Formatting: Black (opinionated) Type Checking: MyPy (strict mode) Testing: Pytest + Coverage + xdist CI/CD: GitHub Actions (multi-platform)

📦 Quick Start for Developers

# Clone repository
git clone https://github.com/umitkacar/SAM-Foundation-Models.git
cd SAM-Foundation-Models

# Install development dependencies
pip install -e ".[dev]"

# Set up pre-commit hooks
pre-commit install

# Run tests
pytest -n auto --cov=src tests/

# Run all quality checks
make check

Full documentation: See DEVELOPMENT.md for complete setup guide

---

🌟 Highlights

⚡ 6x Faster SAM 2 processes images 6x faster than original SAM	🎯 3x Efficient Requires 3x fewer user interactions	📱 30+ FPS Real-time on mobile devices (EdgeSAM)
🏆 ICLR 2025 Best Paper Honorable Mention	🎬 44 FPS Real-time video segmentation	🏥 26+ Tasks Medical imaging benchmarks

---

📑 Table of Contents

Click to expand/collapse

• 🔥 Official Models & Latest Updates
• 🎬 SAM 2 & Video Segmentation
• ⚡ Optimization & Mobile Deployment
• 📚 Academic Research & Surveys
• 💡 Domain-Specific Applications
  • 🏥 Medical Imaging
  • 🛰️ Remote Sensing & Agriculture
  • 🚗 Autonomous Driving & Robotics
  • 🏭 Industrial Quality Control
• 🎓 Training & Fine-Tuning
• 🛠️ Production Deployment & Tools
• 🔧 SAM Extensions & Variants
• 💻 Implementation Libraries
• 📊 Datasets & Benchmarks
• 📖 Educational Resources
• 🎯 Key Insights & Trends

---

🔥 Official Models & Latest Updates

🎯 Meta's Official SAM Family

🌟 SAM 2.1 - Latest Release (September 2024)

Feature	Performance	Status
🚀 Speed	6x faster than SAM 1	✅ Released
🎯 Efficiency	3x fewer interactions	✅ Stable
🎬 Video FPS	44 FPS real-time	✅ Production
📜 License	Apache 2.0	✅ Open Source
🏆 Recognition	ICLR 2025 Best Paper	✅ Awarded

📥 Official Resources

# Install SAM 2
pip install segment-anything-2

# Quick Start
from sam2 import SAM2Model
model = SAM2Model.from_pretrained("facebook/sam2-hiera-large")

Links:

• 📦 GitHub Repository
• 📝 Meta AI Blog
• 📄 Research Paper - ArXiv:2408.00714
• 🤗 HuggingFace Hub - 182K+ downloads/month
• ☁️ AWS SageMaker JumpStart - Feb 2025

🎨 Original SAM (April 2023)

• 🏠 Official Website
• 📦 GitHub Repository
• 📄 Paper - ArXiv:2304.02643
• 🎯 Papers with Code

🔗 Integration Platforms

Platform	Features	Link
🤖 Ultralytics	Production-ready YOLO integration	Docs
🤗 HuggingFace	Model hub, Transformers support	Hub
☁️ SageMaker	AWS deployment ready	JumpStart

---

🎬 SAM 2 & Video Segmentation

🌟 Advanced Video Segmentation (2024-2025)

🏆 SAM2Long ICCV 2025 | 🎯 Training-free memory tree 🔄 Long video segmentation 🎭 Handles occlusion/reappearance 📊 Project Page	🔥 Grounded-SAM-2 Multi-modal Integration | 🤝 Grounding DINO + Florence-2 + SAM 2 🎯 Detect + Segment + Track 🎬 Video object tracking 🌐 HuggingFace ready
🎤 AL-Ref-SAM2 AAAI 2025 | 🔊 Audio-Language-Referenced VOS 🧠 GPT temporal-spatial reasoning 🎯 Training-free paradigm 🚀 State-of-the-art results	🏥 Surgical SAM 2 NeurIPS 2024 | ⚡ 86 FPS real-time 🏥 Medical surgery segmentation 💪 3x faster performance 📱 Resource-constrained ready

📼 Classic Video & Tracking

• 🎯 Segment-and-Track-Anything
• ⚡ RAP-SAM - Real-Time All-Purpose on Video

---

⚡ Optimization & Mobile Deployment

📱 Edge & Mobile Champions

Model	Speed	Size	Device	Highlights
🚀 EdgeSAM	30+ FPS	-	iPhone 14	First mobile SAM @ 30+ FPS
⚡ EfficientSAM	10-20 img/s	9.8M	Edge	Best accuracy-efficiency trade-off
📱 MobileSAM	40x	60x smaller	Mobile	Lightweight variant
🏃 FastSAM	~100 img/s	68M	GPU	Maximum throughput

📊 Performance Comparison: EfficientSAM vs FastSAM

Metric	EfficientSAM-Ti	EfficientSAM-S	FastSAM
COCO AP	45.0 (+4.1)	- (+6.5)	37.0
LVIS AP	- (+5.3)	- (+7.8)	-
Params	9.8M	-	68M
Speed	10-20 img/s	10-20 img/s	~100 img/s

Winner: 🏆 EfficientSAM for accuracy, 🏆 FastSAM for speed

🛠️ Optimization Resources

Click to see optimization tools & papers

📚 Papers & Surveys

• 📄 ArXiv: On Efficient Variants of SAM (2024)
• 🔍 Awesome-Efficient-Segment-Anything

🔗 Repositories

Model	Link	Special Feature
🚀 EdgeSAM	GitHub • Paper	CNN-based, iPhone ready
⚡ EfficientSAM	GitHub • Site	Best AP/params ratio
📱 MobileSAM	GitHub	60x compression
🏃 FastSAM	GitHub • Docs	Prompt-free
🔬 TinySAM	GitHub	Ultra-compact
💎 HQ-SAM	GitHub	NeurIPS 2023, Quality++

---

📚 Academic Research & Surveys

📖 Comprehensive Surveys (2024-2025)

🌟 Must-Read Surveys

📘 A Survey on SAM: Vision Foundation Model Meets Prompt Engineering

ArXiv:2306.06211 • Updated: Oct 2024 • 🏆 Most Comprehensive

📅 Coverage: April 2023 - September 2024
🎯 Topics: SAM & SAM 2, Prompt Engineering
📊 Papers: 200+ analyzed
⭐ Rating: ⭐⭐⭐⭐⭐

📗 A Comprehensive Survey on SAM for Vision and Beyond

ArXiv:2305.08196 • Foundation model analysis

🎯 Topics: Computer Vision Applications
🔬 Depth: Technical Deep Dive
📊 Applications: Multiple Domains

📙 Segment Anything for Video: Past to Future

ArXiv:2507.22792 • 2025 • Video-specific review

🎬 Focus: Video Object Segmentation & Tracking
⏰ Timeline: Past → Present → Future
🎯 Comprehensive VOST analysis

🗂️ Curated Collections

Repository	Description	Stars
📚 Awesome-Segment-Anything	First comprehensive survey
🎬 Awesome-SAM2	SAM 2 specific resources
🏥 SAM4MIS	Medical imaging collection

📑 Paper Lists

• 📄 2024 Paper List - Continuously updated

---

💡 Domain-Specific Applications

🏥 Medical Imaging (2024-2025)

🩺 SAM4MIS CIBM 2024 | Benchmarks: ✅ 15+ medical benchmarks ✅ 26+ different tasks 🔬 Mammography, MRI, CT 👁️ Retinal vessel segmentation 🫀 Ultrasound imaging

🧊 SAM-Med3D General-purpose 3D Medical Segmentation Dataset: 📦 SA-Med3D-140K 🎯 22K 3D images 🏷️ 143K masks 🔬 Multi-modal (CT, MRI, etc.) 🎯 Few-shot 3D prompting

🔬 More Medical Applications

🎯 Key Papers (2024-2025)

Paper	Venue	Application	Performance
Interactive 3D Medical Segmentation	ArXiv 2024	Zero-shot 3D CT	State-of-art
SAM 2 for 3D Medical Imaging	JMIR AI 2025	Abdominal CT scans	Promising
ProtoSAM-3D	PubMed	Volumetric imaging	Interactive
AutoProSAM	WACV 2025	Multi-organ 3D	Automated
SAM-Med2D Analysis	BMC 2024	2D Medical images	Improved

📖 Reviews

• 📚 Review: SAM for Medical Imaging - Comprehensive 2025 review

🛰️ Remote Sensing & Agriculture

🌾 Agricultural Applications

🛰️ SAMGeo

SciPy 2024 Presentation

• 🌍 Automated remote sensing segmentation
• 📦 Open-source geospatial package
• 🎯 User-friendly API

🌱 SAM for Crop Mapping

MDPI Remote Sensing 2024

# Automated sample generation
✅ Sentinel-2 imagery (10m resolution)
✅ Landsat-8 support (30m resolution)
✅ Automatic quality filtering
✅ Sample cleaning pipeline

🚜 Can SAM Recognize Crops?

ArXiv 2023 | Zero-shot Performance Evaluation

• 🎯 Crop-type mapping
• 📊 Precision agriculture
• 🔍 Zero-shot capabilities
• 🌾 Multi-spectral challenges

🗺️ ESRI ArcGIS Integration

• 🏙️ Urban planning
• 🌲 Environmental monitoring
• 💧 Water body extraction
• 🏗️ Infrastructure mapping

🚗 Autonomous Driving & Robotics

🤖 Robotics & AV Applications

🚙 SAMUNet

2025 | Shape-aware 3D Object Detection

• 🎯 Pillar-based detection
• 🚗 Autonomous driving optimized
• 📊 Enhanced 3D understanding

☁️ Point Cloud Resources

• 📊 7 SOTA Point Cloud Models
• 🎯 LiDAR-based detection
• 🤖 Robotic perception
• 🌐 3D scene understanding

Applications:

✅ 3D Object Detection
✅ Semantic Segmentation
✅ Instance Segmentation
✅ Panoptic Segmentation

🏭 Industrial Quality Control

🔍 Defect Detection & QC

⚙️ Weld Defect Detection with SAM

MDPI Sensors 2025

Application: Oil & Gas Pipeline Inspection
Method: Ultrasonic B-scan Analysis
Models: SAM 1 (ViT-Base) + SAM 2 (Hiera-Base+)
Performance: F1-Score 0.940
Defect Type: Lack of Fusion (LOF)

🔧 Armature Defect Detection

MDPI Processes 2025 | YOLO11 + SAM

• 🎯 Micro-vibration motor QC
• 🤖 YOLO11 detection + SAM segmentation
• 📊 Quantitative severity assessment
• ✅ 90%+ accuracy
• ⚡ Real-time capable

Benefits:

✅ Automated inspection
✅ Cost-effective solution
✅ Real-time analysis
✅ Quantitative metrics

🎨 Specialized Domains

🌈 Other Applications

Domain	Project	Description
📏 Depth	Depth-Anything-V2	Monocular depth estimation
🎮 3D Gaussian	gaussian-grouping	3D Gaussian splatting
🏗️ 3D Recon	garfield	3D reconstruction
🔷 Mesh	MeshAnything	3D mesh generation
🎬 4D	SA4D	4D scene understanding
📝 OCR	OCR-SAM	Text recognition
🍕 Food	FOOD-SAM	Food segmentation
📸 Deblur	SAM-Deblur	Image deblurring

---

🎓 Training & Fine-Tuning

🧬 Fine-Tuning Frameworks & LoRA Adapters

🔧 Top Fine-Tuning Repositories

Repository	Method	Domain	Updated
finetune-SAM	LoRA + Full	🏥 Medical	✅ 2024
SAM-fine-tune 🌌	LoRA	🌐 General	✅ Active
lora_sam	LoRA + 🤗	🎯 Vision	✅ 2024
SAMed	LoRA	🏥 Medical	✅ Stable
med-sam-brain	PEFT + LoRA	🧠 Brain Tumor	✅ 2024

📚 Tutorials & Learning Resources

🎯 Official Tutorials

Resource	Level	Topics
Labellerr: SAM + LoRA	🟢 Beginner	One-shot learning, ship segmentation
Encord: Fine-Tune Guide	🟡 Intermediate	Complete pipeline, best practices
Medium: PEFT for Segmentation	🟡 Intermediate	Parameter-efficient methods

📄 Research Papers

• 🔬 Conv-LoRA - OpenReview
  • Lightweight convolutional parameters
  • Combined with LoRA
  • Enhanced performance

💡 Quick Start Example

from transformers import SamModel, SamProcessor
from peft import LoraConfig, get_peft_model

# Load base model
model = SamModel.from_pretrained("facebook/sam-vit-base")

# Configure LoRA
lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    target_modules=["qkv"],
    lora_dropout=0.05,
)

# Apply LoRA
model = get_peft_model(model, lora_config)

# Fine-tune on your data
# ... training code ...

---

🛠️ Production Deployment & Tools

🏷️ Annotation Tools with SAM Integration

✨ CVAT Computer Vision Annotation Tool SAM 2 Integration (2024): 🎬 Video annotation @ 44 FPS 🎯 Semi-automatic segmentation 🚀 Real-time object tracking 🖱️ Interactive prompting Resources: 📝 SAM 2 Video Annotation 🖼️ SAM 2 Image Segmentation

🏷️ Label Studio ML Data Labeling Platform Features: 🤗 HuggingFace Spaces integration 🌐 Multi-modal (image, video, text, audio) 🔐 SSO & RBAC ☁️ Cloud-native ML pipelines 🐳 Docker/Kubernetes deployment Resources: 📝 SAM in HuggingFace Spaces

📊 CVAT vs Label Studio Comparison

Feature	CVAT	Label Studio
Best For	Video annotation, beginners	Enterprise, multi-modal
SAM Integration	✅ SAM 2 native	✅ Via HuggingFace
Video Tools	⭐⭐⭐⭐⭐	⭐⭐⭐
Enterprise	⭐⭐⭐	⭐⭐⭐⭐⭐
Ease of Use	⭐⭐⭐⭐⭐	⭐⭐⭐⭐
ML Pipeline	⭐⭐⭐	⭐⭐⭐⭐⭐
Pricing	Free + Enterprise	Free + Enterprise

🔧 Other Annotation Tools

• 🖥️ AnyLabeling - Desktop labeling with SAM
• 🧂 SALT - Segment Anything Labelling Tool

☁️ Deployment Platforms

🚀 Deployment Options

🤗 HuggingFace Ecosystem

# Install transformers
pip install transformers

# Use SAM with transformers
from transformers import SamModel, SamProcessor

model = SamModel.from_pretrained("facebook/sam-vit-huge")
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")

Resources:

• 📚 Official Docs
• 🎯 Models Hub
• 🚀 Jozu MLOps: HF to Production

🔄 Export & Conversion Tools

Tool	Format	Features
SAM2ONNX	ONNX	SAM 2 converter
sam_onnx_full_export	ONNX	Complete export
sam4onnx	ONNX	Optimization
samexporter	Multi	Multi-format

---

🔧 SAM Extensions & Variants

🎯 Grounding & Multi-Modal

🔥 Popular Extensions

🌟 Grounded-Segment-Anything

The Ultimate Combo:

🎯 Grounding DINO (Detection)
    ↓
🎨 SAM (Segmentation)
    ↓
🖼️ Stable Diffusion (Generation)
    ↓
✨ Detect → Segment → Generate ANYTHING

Features:

• ✅ Text-to-detection
• ✅ Automatic segmentation
• ✅ Image inpainting
• ✅ HuggingFace integration

🛡️ RobustSAM

CVPR 2024 | Adversarial Robustness

• 🔒 Robust to adversarial attacks
• 🎯 Enhanced generalization
• 📊 Better performance on corrupted images

🎨 Personalize-SAM

DreamBooth Integration

• 🎭 Personalized segmentation
• 🤗 Transformers Tutorial
• 📊 vs Mask R-CNN

🧩 Full Pipeline Solutions

Project	Description	Key Feature
SEEM	Segment Everything Everywhere	Universal segmentation
Full-SAM	Complete pipeline	End-to-end solution
AUTODISTILL	Auto labeling	Dataset generation
GroundingDINO	Language grounding	Text-guided detection
RAM	Recognize Anything	Image tagging
CLIP	Vision-Language	Foundation model

---

💻 Implementation Libraries

🔤 Multi-Language Support

⚙️ C++ Implementations

Repository	Framework	Platform
segment-anything-cpp-wrapper	Pure C++	Cross-platform
sam-cpp-macos	Extended	macOS
sam.cpp	GGML	Multi-platform
SegmentAnything-OnnxRunner	ONNX	Cross-platform
SAM-ONNX-AX650-CPP	QT + Lama	GUI + Inpaint

🔷 Other Languages

C#

• 💎 SamSharp - C# implementation

Rust 🦀

• ⚡ sam_onnx_rust - Rust ONNX

LibTorch 🔥

• 🎯 Libtorch-MobileSAM-Example - C++ PyTorch

📱 Mobile Runtimes

MNN Framework

• 📱 EdgeSAM-MNN - EdgeSAM on MNN
• 🚀 mnn-segment-anything - Mobile Neural Network

🎨 Creative Tools Integration

ComfyUI

• 🎭 comfyui_segment_anything - SAM nodes for ComfyUI workflow

---

📊 Datasets & Benchmarks

🗄️ Official Meta Datasets

SA-1B (Images)	SA-V (Videos)
📦 SA-1B Dataset Images: 11 Million Masks: 1+ Billion Type: Open world images License: Licensed & privacy-respecting Status: ✅ Released 2023 Superlatives: 🏆 Largest segmentation dataset 🌍 Diverse geography 🎯 High-quality annotations	🎬 SA-V Dataset Videos: 51,000 Countries: 47 Masks: 600,000+ Resolution: 240p → 4K Duration: 4s → 138s Status: ✅ Released 2024 Features: 🌍 Global diversity 🎥 Multi-resolution ⏱️ Variable length

🎯 Benchmark Datasets

📊 SAM 2 Evaluation Benchmarks

Benchmark	Task	Metrics
DAVIS	Video object segmentation	J&F score
MOSE	Multi-object segmentation	J&F score
LVOS	Long-term video segmentation	Success rate
YouTube-VOS	Large-scale video	J&F score
COCO	Instance segmentation	AP, AR
LVIS	Large vocabulary segmentation	AP, APr

SAM 2 Performance:

✅ 3x fewer interactions
✅ Better accuracy
✅ 6x faster inference
✅ SOTA on all benchmarks

---

📖 Educational Resources & Tutorials

🎓 Learn SAM from Scratch to Production

📚 Comprehensive Guides

🌟 Must-Read Tutorials

Resource	Level	Topics	Link
🎯 Encord Ultimate Guide	🟢 All	Architecture, Training, Applications	Read
🤖 Roboflow Breakdown	🟢 Beginner	Concepts, Use Cases	Read
🛠️ Roboflow How-to	🟡 Intermediate	Practical Implementation	Read
🏷️ V7 Labs Guide	🟢 All	Complete Overview	Read
👨‍💻 LabelVisor Hands-on	🟡 Intermediate	Effortless Segmentation	Read

⚡ Performance & Optimization

🚀 Optimization Deep Dives

📊 Comparison Articles

• 📈 EfficientSAM vs SAM - Detailed comparison
• 🏃 Fast Faster SAM - Speed optimization
• 📱 Faster SAM for Mobile - Mobile deployment
• 🔍 SAM and Friends - Model ecosystem

🎥 Video Resources

📺 YouTube Channels

Channel	Focus	Subscriber Count
Rob Mulla	ML Tutorials, SAM Applications	Data Science
ArjanCodes	Software Engineering, Clean Code	Python & AI

---

🎯 Key Insights & Trends (2024-2025)

🚀 Major Developments Timeline

timeline
    title SAM Evolution 2024-2025
    2024-07 : SAM 2 Release
           : Video Segmentation
    2024-09 : SAM 2.1 Update
           : ICLR 2025 Award
    2024-12 : Medical Breakthrough
           : 26+ Tasks, 15+ Benchmarks
    2025-02 : AWS Integration
           : SageMaker JumpStart

Loading

📊 Performance Benchmarks

Metric	Value	Model
⚡ Speed Improvement	6x faster	SAM 2 vs SAM 1
🎯 Efficiency Gain	3x fewer interactions	SAM 2
📱 Mobile FPS	30+ FPS	EdgeSAM (iPhone 14)
🎬 Video FPS	44 FPS	SAM 2 real-time
🏥 Surgical FPS	86 FPS	Surgical SAM 2
🏭 Industrial Accuracy	F1: 0.940	Weld Defect Detection
🎓 Medical Tasks	26+ tasks	SAM4MIS

🔬 Research Trends

🌟 Emerging Research Directions

🎯 Key Trends 2024-2025

1. 🚀 Training-Free Adaptation
   └─ LoRA, Conv-LoRA, Prompt Tuning

2. 🎬 Video Understanding
   └─ SAM 2, SAM2Long, Temporal Consistency

3. 🏥 Medical Imaging
   └─ 3D Segmentation, Multi-modal Fusion

4. 📱 Edge Deployment
   └─ Quantization, Pruning, Distillation

5. 🌐 Multi-Modal Integration
   └─ Audio-Visual, Language-Vision

6. 🎯 Zero-Shot Transfer
   └─ Cross-domain, Few-shot Learning

7. 🎮 3D/4D Understanding
   └─ Point Clouds, Temporal Dynamics

📈 Growth Areas

Domain	Growth	Key Applications
🏥 Medical	⭐⭐⭐⭐⭐	3D imaging, Surgery
🚗 Autonomous	⭐⭐⭐⭐	LiDAR, Perception
🛰️ Remote Sensing	⭐⭐⭐⭐	Agriculture, Mapping
🏭 Industrial	⭐⭐⭐⭐⭐	QC, Defect Detection
🎨 Creative	⭐⭐⭐	Editing, Generation

---

🎨 "Anything" Projects Ecosystem

💫 2024 Innovative Projects

🌟 Click to explore 2024 projects

Project	Description	Stars
ReplaceAnything	🎭 Replace objects in images
Depth-Anything	📏 Monocular depth estimation
OMG-Seg	🌍 Open-world segmentation
OVSAM	📖 Open-vocabulary SAM

🎯 2023 Classic Projects

📚 Essential 2023 projects

🎨 Creative & Editing

• Matting-Anything - Professional image matting
• Inpaint-Anything - Intelligent inpainting
• EditAnything - Flexible image editing
• Painter - Generative models

🔍 Detection & Segmentation

• Prompt-Segment-Anything - Advanced prompting
• Semantic-Segment-Anything - Semantic seg
• Segment-Any-Anomaly - Anomaly detection
• GroundedSAM-Anomaly - Zero-shot AD

📊 Analysis & Understanding

• Caption-Anything - Image captioning
• Count-Anything - Object counting
• detect-anyshadow - Shadow detection
• ShowAnything - Visualization

🎮 3D & Reconstruction

• Anything-3D - 3D reconstruction

---

🤝 Contributing

💡 Help Us Grow This Collection!

We welcome contributions! Please ensure:

• ✅ Resources are from reputable sources
• ✅ Links are active and high-quality
• ✅ Descriptions are accurate and concise
• ✅ Proper categorization
• ✅ Include relevant badges/stars
• ✅ Add performance metrics when available

---

📄 Citation

📝 BibTeX Citations

SAM (Original)

@article{kirillov2023segment,
  title={Segment Anything},
  author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
  journal={arXiv:2304.02643},
  year={2023}
}

SAM 2

@article{ravi2024sam2,
  title={SAM 2: Segment Anything in Images and Videos},
  author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Doll{\'a}r, Piotr and Feichtenhofer, Christoph},
  journal={arXiv:2408.00714},
  year={2024}
}

---

📚 Documentation & Resources

📖 Core Documentation DEVELOPMENT.md - Complete developer guide SETUP_INSTRUCTIONS.md - Quick start guide CHANGELOG.md - Detailed change history lessons-learned.md - Project insights & best practices

📋 Status & Setup CURRENT_STATUS.md - Repository status GITHUB_WORKFLOW_SETUP.md - CI/CD setup Makefile - Developer commands pyproject.toml - Project configuration

🎯 Repository Status

Latest Release: v1.0.0 | Status: ✅ Production Ready | Last Updated: November 2025

---

🌟 Star History

---

📊 Repository Stats

---

Last Updated: January 2025 🗓️ Maintainer: Community-driven 👥 License: Collection of resources with individual licenses 📜

---

_{Disclaimer: This is a curated collection. Each project has its own license.}

⭐ Star this repo to stay updated with the latest SAM developments!

👀 Watch for new resources and updates!

Made with ❤️ by the SAM Community