Yutong-Zhou-cv / Investigation-of-SAM

This is an investigation and collection of the Segment Anything Model (SAM) on real-world applications.

Investigation-of-SAM🤔

This is an investigation and collection of the Segment Anything Model (SAM) on real-world applications.

🎑 News

• [23/04/19] "Investigation-of-SAM" repo is created. Add the representative projects.

🍵 To Do

• • Add some details and tips for each project
• • Add paper with code
• • Add some images
• • Add more details and some tips for each paper

Content

• • 1. Introduction
• • 2. Related Paper
  • • Survey
  • • 2023
• • 3. Related Project

1.Introduction

Segment Anything

Meta AI Research, FAIR

Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick

[Paper] | [Project] | [Code] | [Demo] | [Dataset] | [Blog]

Segment Anything Model (SAM): a new AI model from Meta AI that can "cut out" any object, in any image, with a single click. SAM is a promptable segmentation system with zero-shot generalization to unfamiliar objects and images, without the need for additional training.

2. Related Paper

Survey

• A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering [v1](arXiv-2023.06)
• A Comprehensive Survey on Segment Anything Model for Vision and Beyond [v1](arXiv-2023.05)
• Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications [v1](arXiv-2023.04) ... [v3](CVPRW-2023.05)

2023

• (arXiv preprint 2023) Fast Segment Anything [Paper] [Code]

3. Related Project

• [🚩Semantic Segment] Semantic Segment Anything [Official repo] | [Web Demo]
• [🚩Edit & Generate] Edit Anything [Official repo] | [Hugging Face]
• [🚩Image-to-Paragraph] Image2Paragraph [Official repo] | [Hugging Face] | [Colab]
• [🚩Detect & Segment] Grounded-Segment-Anything [Official repo] | [Hugging Face] | [Colab]
• [🚩Part-level Segment] Grounded Segment Anything: From Objects to Parts [Official repo] | [Blog]
• [🚩Inpaint] Inpaint Anything [Official repo] | [Paper]-Inpaint Anything: Segment Anything Meets Image Inpainting
• [🚩Relationship] Relate Anything [Official repo] | [Hugging Face] | [Dataset]
• [🚩Optical Character Recognition] OCR-SAM [Official repo]
• [🚩Semantic Segment] Fast Segment Anything [Official repo] | [Hugging Face]
• OpenMMLab Playground
  • [🚩Object Detection] MMDet-SAM
  • [🚩Oriented Object Detection] MMRotate-SAM
  • [🚩Optical Character Recognition] MMOCR-SAM
  • [🚩Video Editing] MMEditing-SAM
  • [🚩Point-to-Label] Label-Studio-SAM