A Comprehensive Survey on Segment Anything Model for Vision and Beyond

Thanks a lot for releasing such an amazing work!

To fully understand SAM, we conduct a [survey study](https://arxiv.org/abs/2305.08196).
- We first introduce the background and terminology for foundation models including SAM, as well as state-of-the-art methods contemporaneous with SAM that are significant for segmenting anything task.
- Then, we analyze and summarize the advantages and limitations of SAM across various image processing applications, including software scenes, real-world scenes, and complex scenes.
- We also summarize massive other amazing applications of SAM in vision and beyond.
- Finally, we maintain a continuously updated paper list for segment anything foundation models at [here](https://github.com/liliu-avril/Awesome-Segment-Anything).

Through statistics, we have made some interesting discoveries.
- SAM for Medical Imaging has received the most attention from the AI community, with 24 papers so far, accounting for 40% of SAM-based papers.
- SAM is also widely used in fields other than traditional vision, such as 3D Reconstruction, Non-Euclidean Domain, and Vision-Language tasks.

This survey will be regularly updated to reflect the dynamic progress of the foundational model of SAM during its development.

Start by reading the linked survey and the continuously updated paper list to understand how they relate to this repository. No repository file, test, requested change, or acceptance criterion is identified, so the scope and definition of done would need clarification before implementation.

Written by the indexing model from the issue text.