{"id":46220,"url":"https://github.com/hedlen/awesome-segment-anything","name":"awesome-segment-anything","description":"Tracking and collecting papers/projects/others related to Segment Anything.","projects_count":87,"last_synced_at":"2026-10-01T04:00:21.663Z","repository":{"id":152762646,"uuid":"626723712","full_name":"Hedlen/awesome-segment-anything","owner":"Hedlen","description":"Tracking and collecting papers/projects/others related to Segment Anything.","archived":false,"fork":false,"pushed_at":"2026-04-26T03:57:08.000Z","size":12102,"stargazers_count":1700,"open_issues_count":0,"forks_count":128,"subscribers_count":61,"default_branch":"main","last_synced_at":"2026-09-24T08:50:27.922Z","etag":null,"topics":["application","awesome-list","chatgpt","image-generation","inpainting","object-detection","segment-anything","segmentation","stable-diffusion","suvey"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Hedlen.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-04-12T03:16:37.000Z","updated_at":"2026-09-15T16:44:01.000Z","dependencies_parsed_at":"2024-01-14T09:17:55.591Z","dependency_job_id":"52c7f844-aeb8-453c-94fd-06c9c70bffcc","html_url":"https://github.com/Hedlen/awesome-segment-anything","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Hedlen/awesome-segment-anything","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hedlen%2Fawesome-segment-anything","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hedlen%2Fawesome-segment-anything/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hedlen%2Fawesome-segment-anything/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hedlen%2Fawesome-segment-anything/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Hedlen","download_url":"https://codeload.github.com/Hedlen/awesome-segment-anything/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Hedlen%2Fawesome-segment-anything/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":342085742,"owners_count":37893434,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-10-01T02:00:06.691Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-14T09:17:50.275Z","updated_at":"2026-10-01T04:00:21.663Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Papers/Projects","πŸ…Recognition"],"sub_categories":["Basemodel Papers","Derivative Papers","Derivative Projects","front-end framework"],"readme":"\n\u003cdiv align=\"center\"\u003e\n\u003cbr\u003e\n\u003cimage src=\"./imgs/teaser.png\", width=\"600px\", height=\"287px\"\u003e\n\u003cbr\u003e\n\u003c/div\u003e\n\u003c!-- ![img](./imgs/teaser.png) --\u003e\n\n# Awesome Segment Anything [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)\nSegment Anything has led to a new breakthrough in the field of Computer Vision (CV), and this repository will continue to track and summarize the research progress of Segment Anything in various fields, including Papers/Projects, etc. \n\nIf you find this repository helpful, please consider Stars ⭐ or Sharing ⬆️. Thanks.\n## πŸ…Recognition \nThis repository has been featured on [Shypd.Ai](https://shypd.ai/e/awesome-segment-anything), the largest open index of AI tools worldwide (over 80,000 tools). It is categorized under Academic Research, an emerging section that currently hosts fewer than 1,800 high-quality AI resources.\n\n## News\n- 2026.4: Added RankSEG (NeurIPS 2025 \u0026 JMLR 2023), EfficientSAM (CVPR 2024), EdgeSAM, Semantic-SAM, MedSAM-2, SurgicalSAM (AAAI 2024) and more.\n- 2025.11.19: Added SAM 3 - Meta's latest breakthrough in visual segmentation with text-based prompting and concept-level understanding.\n- 2024.9: Added SAM 2.1 - Enhanced version with improved video segmentation and training code release.\n- 2024.8.16: Added Segment Anything 2 (SAM 2) and SaLIP - First unified model for real-time object segmentation in images and videos.\n- 2023.8.29: Updated with recent works and expanded derivative papers section.\n- 2023.5.20: Updated document structure and added robotics-related article. Happy 520 Day!\n- 2023.5.4: Added SEEM - Segment Everything Everywhere All at Once.\n- 2023.4.18: Added Inpainting Anything and SAM-Track for video segmentation.\n- 2023.4.12: Initial release tracking SAM papers and projects.\n\n## Contents\n\n- [Basemodel Papers](#basemodel-papers) \n- [Derivative Papers](#derivative-papers)\n - [Analysis and Expansion of SAM](#analysis-and-expansion-of-sam)\n - [Medical Image Segmentation](#medical-image-segmentation)\n - [Inpainting](#inpainting)\n - [Camouflaged Object Detection](#camouflaged-object-detection)\n - [Video Frame Interpolation](#video-frame-interpolation)\n - [Low Level Vision](#low-level-vision)\n - [Image Matting](#image-matting)\n - [Robotic](#robotic)\n - [Bioinformatics](#bioinformatics)\n - [3D](#3d)\n - [Remote Sensing](#remote-sensing)\n - [Tracking](#tracking)\n - [Audio-visual Localization and Segmentation](#audio-visual-ocalization-and-segmentation)\n - [Adversarial Attacks](#adversarial-attacks)\n - [LLM and SAM](#llm-and-sam)\n - [Autonomous Driving](#autonomous-driving)\n- [Derivative Projects](#derivative-projects) \n - [Image Segmentation task](#image-segmentation-task)\n - [Video Segmentation task](#video-segmentation-task)\n - [Medical image Segmentation task](#medical-image-segmentation-task)\n - [Inpainting task](#inpainting-task)\n - [3D task](#3d-task)\n - [Image Generation task](#image-generation-task)\n - [Remote Sensing task](#remote-sensing-task)\n - [Moving Object Detection task](#moving-object-detection-task)\n - [OCR task](#ocr-task)\n- [front-end framework](#front-end-framework)\n - [JS SDK for SAM](#samjs)\n\n## Papers/Projects\n### Basemodel Papers\n| Title | Presentation | Paper page | Project page | Code base | Affiliation | Description |\n| :------------------------------------------------:| :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| :---------------------------------------------:| :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:| :-----------------------------------------------------------------------------------:| :-----------:| :---------------------------------------------------------------------------------------------------------:|\n| CLIP | ![img](./imgs/clip.png) | [arXiv](https://arxiv.org/abs/2103.00020) | [Colab](https://colab.research.google.com/github/openai/clip/blob/master/notebooks/Interacting_with_CLIP.ipynb) | [Code](https://github.com/openai/CLIP) | OpenAI | Contrastive Language-Image Pre-Training. |\n| OWL-ViT | ![img](https://github.com/google-research/scenic/raw/main/scenic/projects/owl_vit/data/text_cond_wiki_stillife_1.gif) | [ECCV2022](https://arxiv.org/abs/2205.06230) | - | [Code](https://github.com/google-research/scenic/tree/main/scenic/projects/owl_vit) | Google | A open-vocabulary object detector. |\n| OvSeg | ![img](https://github.com/facebookresearch/ov-seg/raw/main/resources/ovseg.gif) | [CVPR2023](https://arxiv.org/abs/2210.04150) | [Project](https://jeff-liangf.github.io/projects/ovseg/) | [Code](https://github.com/facebookresearch/ov-seg) | META | Segment an image into semantic regions according to text descriptions. |\n| Painter | ![img](https://github.com/baaivision/Painter/raw/main/Painter/docs/teaser.jpg) | [CVPR2023](https://arxiv.org/abs/2212.02499) | - | [Code](https://github.com/baaivision/Painter) | BAAI | A Generalist Painter for In-Context Visual Learning. |\n| Grounding DINO | ![img](https://github.com/IDEA-Research/GroundingDINO/raw/main/.asset/hero_figure.png) | [arXiv](https://arxiv.org/abs/2303.05499) | [Colab](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb) \u0026[Huggingface](https://huggingface.co/spaces/ShilongLiu/Grounding_DINO_demo) | [Code](https://github.com/IDEA-Research/GroundingDINO) | IDEA | A stronger open-set object detector |\n| Segment Anything | ![img](https://github.com/facebookresearch/segment-anything/raw/main/assets/model_diagram.png?raw=true)![img](https://github.com/facebookresearch/segment-anything/raw/main/assets/masks2.jpg?raw=true) | [arXiv](https://arxiv.org/abs/2304.02643) | [Project page](https://segment-anything.com/) | [Code](https://github.com/facebookresearch/segment-anything) | Meta | A stronger Large model which can be used to generate masks for all objects in an image. |\n| SegGPT | ![img](https://github.com/baaivision/Painter/raw/main/SegGPT/seggpt_teaser.png) | [arXiv](https://arxiv.org/abs/2304.03284) | [Project page](https://huggingface.co/spaces/BAAI/SegGPT) | [Code](https://github.com/baaivision/Painter) | BAAI | Segmenting Everything In Context based on Painter. |\n| Segment Everything Everywhere All at Once (SEEM) | ![img](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/raw/main/assets/teaser_new.png?raw=true) | [arXiv](https://arxiv.org/pdf/2304.06718.pdf) | [Project Page](https://huggingface.co/spaces/xdecoder/SEEM) | [Code](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once) | Microsoft | Semantic Segmentation with various prompt types. |\n| Segment Anything 2 (SAM 2) | ![img](https://github.com/facebookresearch/segment-anything-2/blob/main/assets/model_diagram.png?raw=true) | [Paper](https://ai.meta.com/sam2/) | [Project Page](https://ai.meta.com/sam2/) | [Code](https://github.com/facebookresearch/segment-anything-2) | Meta | A foundation model towards solving promptable visual segmentation in images and videos. |\n| SAM 3 | - | [arXiv](https://arxiv.org/abs/2511.16719) | [Project Page](https://huggingface.co/papers/2511.16719) | - | Meta | Segment Anything with Concepts: doubles accuracy on promptable concept segmentation in images and videos. |\n\n### Derivative Papers\n\n#### Analysis and Expansion of SAM\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| CLIP_Surgery | ![img](https://github.com/xmed-lab/CLIP_Surgery/raw/master/figs/fig4.jpg)| [arXiv](https://arxiv.org/pdf/2304.05653.pdf) |[Demo](https://github.com/xmed-lab/CLIP_Surgery/blob/master/demo.ipynb)| [Code](https://github.com/xmed-lab/CLIP_Surgery) | HKUST | This work about SAM based on CLIP's explainability to achieve text to mask without manual points.|\n| GenSAM | ![img](https://github.com/jyLin8100/GenSAM/blob/main/AIG_framework_v2.png) | [arXiv](https://arxiv.org/abs/2312.07374) | [Project Page](https://lwpyh.github.io/GenSAM/) | [Code](https://github.com/jyLin8100/GenSAM) | QMUL | This work relaxes the requirement for instance-specific prompts in SAM.|\n| Segment Anything Is Not Always Perfect | ![img](./imgs/sainap.png) | [arXiv](https://arxiv.org/pdf/2304.05750.pdf) | - | - | Samsung | This paper analyzes and discusses the benefits and limitations of SAM.|\n| PerSAM | ![img](https://github.com/ZrrSkywalker/Personalize-SAM/blob/main/figs/fig_persam.png) | [arXiv](https://arxiv.org/abs/2305.03048) | [Project Page](https://huggingface.co/papers/2305.03048) | [Code](https://github.com/ZrrSkywalker/Personalize-SAM) | - | Segment Anything with specific concepts. |\n| Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching | ![img1](https://github.com/aim-uofa/Matcher/blob/main/figs/framework.png) | [arXiv](https://arxiv.org/abs/2305.13310) | - | [Code](https://github.com/aim-uofa/Matcher) | - | One shot semantic segmentation by integrating an all-purpose feature extraction model and a class-agnostic segmentation model. |\n| Segment Anything in High Quality | ![img](./imgs/HQ-SAM.png) | [NeurIPS2023](https://arxiv.org/pdf/2306.01567.pdf) | [Project Page](https://huggingface.co/papers/2306.01567) | [Code](https://github.com/SysCV/sam-hq) | ETH ZΓΌrich \u0026 HKUST | HQ-SAM: improve segmentation quality of SAM using learnable High-Quality Output Token. |\n| Detect Any Shadow: Segment Anything for Video Shadow Detection | ![img](./imgs/Detect-AnyShadow.png) | [arXiv](https://arxiv.org/pdf/2305.16698.pdf) | - | [Code](https://github.com/harrytea/Detect-AnyShadow) | University of Science and Technology of China | Use SAM to detect initial frames then use an LSTM network for subsequent frames. |\n| Fast Segment Anything | ![img](https://github.com/CASIA-IVA-Lab/FastSAM/raw/main/assets/head_fig.png) | [arXiv](https://arxiv.org/pdf/2306.12156v1.pdf) | [Project Page](https://huggingface.co/spaces/An-619/FastSAM) | [Code](https://github.com/casia-iva-lab/fastsam) | - | Reformulate the architecture and improve the speed of SAM. | \n| MobileSAM (Faster Segment Anything) | ![img](https://github.com/ChaoningZhang/MobileSAM/blob/master/assets/model_diagram.jpg?raw=true) | [arXiv](https://arxiv.org/pdf/2306.14289.pdf) | [Project Page](https://huggingface.co/papers/2306.14289) | [Code](https://github.com/ChaoningZhang/MobileSAM) | Kyung Hee University | Make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one.|\n| FoodSAM (Any Food Segmentation) | ![img](https://github.com/jamesjg/FoodSAM/blob/main/assets/model.jpg) | [arXiv](https://arxiv.org/abs/2308.05938) | [Project Page](https://starhiking.github.io/FoodSAM_Page/) | [Code](https://github.com/jamesjg/FoodSAM) | UCAS | Semantic, instance, panoptic, interactive segmentation on food image.|\n| DefectSAM | ![img](./imgs/DefectSAM-model.png) | [arXiv](https://arxiv.org/abs/2311.10245) | - | [Code](https://github.com/bozhenhhu/DefectSAM) | ZJU, Westlake, UESTC, etc. | Infrared thermal images, defect detection.|\n| SlimSAM | ![img](https://github.com/czg1225/SlimSAM/blob/master/images/paper/intro.PNG) | [arXiv](https://arxiv.org/abs/2312.05284) | - | [Code](https://github.com/czg1225/SlimSAM) | NUS | 0.1% Data Makes Segment Anything Slim.|\n| EfficientSAM | ![img](https://github.com/yformer/EfficientSAM/raw/main/figs/efficient_sam_framework.png) | [CVPR2024](https://arxiv.org/abs/2312.00863) | [Project Page](https://huggingface.co/papers/2312.00863) | [Code](https://github.com/yformer/EfficientSAM) | Meta | Lightweight SAM models via masked image pretraining (SAMI), achieving competitive performance with greatly reduced complexity. |\n| EdgeSAM | ![img](https://github.com/chongzhou96/EdgeSAM/raw/master/assets/teaser.png) | [arXiv](https://arxiv.org/abs/2312.06660) | [Project Page](https://mmlab-ntu.com/project/edgesam/) | [Code](https://github.com/chongzhou96/EdgeSAM) | MMLab@NTU | Prompt-in-the-loop distillation for on-device SAM deployment; 40Γ— faster than SAM, first to run \u003e30 FPS on iPhone 14. |\n| Semantic-SAM | ![img](https://github.com/UX-Decoder/Semantic-SAM/raw/main/assets/teaser.png) | [arXiv](https://arxiv.org/abs/2307.04767) | [Project Page](https://huggingface.co/papers/2307.04767) | [Code](https://github.com/UX-Decoder/Semantic-SAM) | Microsoft | Universal image segmentation model that segments and recognizes anything at any desired granularity. |\n| RankSEG | ![img](https://github.com/rankseg/rankseg/raw/main/fig/example1.jpeg) | [NeurIPS 2025](https://openreview.net/forum?id=4tRMm1JJhw) / [JMLR 2023](https://jmlr.org/papers/v24/22-0712.html) | [Docs](https://rankseg.readthedocs.io/en/latest/) / [Demo](https://huggingface.co/spaces/statmlben/rankseg) | [Code](https://github.com/rankseg/rankseg) / [Colab](https://colab.research.google.com/drive/1Gj-rG3ZnFN5OYTcgdJHfUuiSJtWVpgfu?usp=sharing) | CUHK | **RankSEG** is a **plug-and-play** post-processing module that improves segmentation results during inference. It works with segmentation models (SAM, DeepLab, SegFormer, UPerNet, etc.) without any retraining or fine-tuning. |\n\n#### Medical Image Segmentation\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Segment Anything Model (SAM) for Digital Pathology | ![img](./imgs/samdp.png) | [arXiv](https://arxiv.org/abs/2304.04155) | - | - | - | SAM + Tumor segmentation/Tissue segmentation/Cell nuclei segmentation. |\n| Segment Anything in Medical Images | ![img1](./imgs/sami.png)| [arXiv](https://arxiv.org/pdf/2304.12306.pdf)| - |[Code](https://github.com/bowang-lab/MedSAM) | - | A step-by-step tutorial with a small dataset to help you quickly utilize SAM.|\n| SAM Fails to Segment Anything? | ![img1](https://camo.githubusercontent.com/bae32a4f7f7b6cf23aafde7f574ef96544b87f59196c9aa125f93240bb178b36/68747470733a2f2f7469616e72756e2d6368656e2e6769746875622e696f2f53414d2d41646170746f722f7374617469632f696d616765732f706f6c79702e6a7067)| [arXiv](https://arxiv.org/pdf/2304.09148.pdf)| - |[Code](https://github.com/tianrun-chen/SAM-Adapter-PyTorch) | - | SAM-adapter: Adapting SAM in Underperformed Scenes: Camouflage, Shadow, Medical Image Segmentation, and More.|\n| Segment Anything Model for Medical Image Analysis: an Experimental Study | ![img1](./imgs/sam_on_medical_image_study.png) | [arXiv](https://arxiv.org/pdf/2304.10517.pdf) | - | - | - | Thorough experiments evaluating how SAM performs on 19 medical image datasets. |\n| Medical-SAM-Adapter | ![img1](https://github.com/WuJunde/Medical-SAM-Adapter/raw/main/figs/medsamadpt.jpeg) | [arXiv](https://arxiv.org/abs/2304.12620.pdf) | - | [Code](https://github.com/KidsWithTokens/Medical-SAM-Adapter) | - | A project to finetune SAM using Adaption for the Medical Imaging. |\n| SAM-Med2D | ![img1](https://github.com/OpenGVLab/SAM-Med2D/blob/main/assets/visualization.png) | [arXiv](https://arxiv.org/abs/2308.16184) | - | [Code](https://github.com/OpenGVLab/SAM-Med2D) | Sichuan University \u0026 Shanghai AI Laboratory | The most comprehensive studies on applying SAM to medical 2D images. |\n| ScribblePrompt-SAM | ![img1](https://github.com/halleewong/ScribblePrompt/blob/website/assets/gifs/total_segmentator.gif) | [arXiv](https://arxiv.org/abs/2312.07381) | [Project Page](https://scribbleprompt.csail.mit.edu/) | [Code](https://github.com/halleewong/ScribblePrompt) | MIT \u0026 MGH | Fine-tuned SAM on 65 biomedical imaging datasets with scribble, click, and bounding box inputs. |\n| SaLIP | - | [arXiv](https://arxiv.org/abs/2404.06362) | - | [Code](https://github.com/aleemsidra/SaLIP) | - | Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero-shot Medical Image Segmentation. |\n| MedSAM-2 | - | [arXiv](https://arxiv.org/abs/2408.00874) | - | [Code](https://github.com/MedSAM2/MedSAM2) | - | Medical SAM 2: treats all 2D and 3D medical segmentation tasks as video object tracking, enabling universal auto-tracking segmentation. |\n| SurgicalSAM | ![img](https://github.com/wenxi-yue/SurgicalSAM/raw/main/assets/framework.png) | [AAAI2024](https://arxiv.org/abs/2308.08746) | - | [Code](https://github.com/wenxi-yue/SurgicalSAM) | University of Adelaide | Efficient class-promptable surgical instrument segmentation by fine-tuning SAM with surgical-specific information, eliminating the need for explicit point/box prompts. |\n\n#### Bioimage Analysis\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Segment Anything for Microscopy | ![img](https://github.com/computational-cell-analytics/micro-sam/blob/master/doc/images/lm_comparison.png) | [bioRxiv](https://doi.org/10.1101/2023.08.21.554208) | [Demo](https://computational-cell-analytics.github.io/micro-sam/micro_sam.html#installation) | [Code](https://github.com/computational-cell-analytics/micro-sam) | University of GΓΆttingen, Germany | Segment Anything for Microscopy implements automatic and interactive annotation for microscopy data. It is built on top of Segment Anything and specializes it for microscopy and other bio-imaging data. Its core components are: \u003cul\u003e\u003cli\u003eThe `micro_sam` tools for interactive data annotation with napari.\u003c/li\u003e\u003cli\u003eThe `micro_sam` library to apply Segment Anything to 2d and 3d data or fine-tune it on your data.\u003c/li\u003e\u003cli\u003eThe `micro_sam` models that are fine-tuned on publicly available microscopy data.\u003c/li\u003e Our goal is to build fast and interactive annotation tools for microscopy data. |\n\n#### Inpainting\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Inpaint Anything | ![img1](./imgs/ia.png)| [arXiv](https://arxiv.org/abs/2304.06790)| - |[Code](https://github.com/geekyutao/Inpaint-Anything) | USTC \u0026 EIT | SAM + Inpainting, which is able to remove the object smoothly.|\n| SAM + Stable Diffusion for Text-to-Image Inpainting | ![img1](https://www.comet.com/site/wp-content/uploads/2023/06/Screen-Shot-2023-06-19-at-2.40.49-PM.png) | - | [Project](https://www.comet.com/examples/demo-text-to-inpainting-sam-stablediffusion/view/bRnI022tXQUdKGsVCFmjFRRtT/) | [Code](https://colab.research.google.com/drive/1B7L4cork9UFTtIB02EntjiZRLYuqJS2b#scrollTo=LtZghyHoJabf) | comet | Grounding DINO + SAM + Stable Diffusion. |\n\n#### Camouflaged Object Detection\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| SAMCOD | - | [arXiv](https://arxiv.org/abs/2304.04709) | - | [Code](https://github.com/luckybird1994/SAMCOD) | - | SAM + Camouflaged object detection (COD) task.|\n\n#### Video Frame Interpolation\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation | ![img](https://github.com/zzh-tech/InterpAny-Clearer/blob/site/docs/static/InterpAny-Clearer-Demo-Small.gif) | [arXiv](https://arxiv.org/abs/2311.08007) | [Project Page](https://zzh-tech.github.io/InterpAny-Clearer/) \u0026 [Interactive Demo](http://ai4sports.opengvlab.com/interpany-clearer/) | [Code](https://github.com/zzh-tech/InterpAny-Clearer) | Shanghai AI Laboratory \u0026 Snap Inc. | Editable video frame interpolation with SAM. |\n\n#### Low Level Vision\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Segment Anything in Video Super-resolution | ![img1](./imgs/sam_vsr.png)| [arXiv](https://arxiv.org/pdf/2305.06524.pdf)| - | - | - | The first step to use SAM for low-level vision.|\n| SAM-IQA | ![img1](./imgs/sam-iqa.png)| [arXiv](https://arxiv.org/pdf/2307.04455.pdf)| - | [Code](https://github.com/Hedlen/SAM-IQA) | Megvii | The first to introduce the SAM in IQA and demonstrate its strong generalization ability in this domain.|\n\n#### Image Matting\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Matte Anything | ![img](https://github.com/hustvl/Matte-Anything/blob/main/figs/matte-anything.png)![img](https://user-images.githubusercontent.com/74295796/244441627-d947f59d-b0c1-4c22-9967-d8f2bf633879.gif)| [arXiv](https://arxiv.org/abs/2306.04121)| - | [Code](https://github.com/hustvl/Matte-Anything)| HUST Vision Lab| An interactive natural image matting system with excellent performance for both opaque and transparent objects. |\n| Matting Anything | ![img1](https://github.com/SHI-Labs/Matting-Anything/raw/main/assets/teaser_arxiv_v2.png) | [arXiv](https://arxiv.org/abs/2306.05399) | [Project page](https://huggingface.co/papers/2306.05399) | [Code](https://github.com/SHI-Labs/Matting-Anything) | SHI Labs | Leverage feature maps from SAM and adopts a Mask-to-Matte module to predict the alpha matte. |\n\n#### Robotic\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Instruct2Act | ![img1](https://github.com/OpenGVLab/Instruct2Act/raw/main/images/instruct2act_framework.png)| [arXiv](https://arxiv.org/pdf/2305.11176.pdf)| - | [Code](https://github.com/OpenGVLab/Instruct2Act) | OpenGVLab | A SAM application in the Robotic field.|\n\n#### Bioinformatics\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| IAMSAM | ![img1](https://github.com/portrai-io/IAMSAM/blob/main/assets/screenshot.png)| [bioRxiv](https://www.biorxiv.org/content/10.1101/2023.05.25.542052v1)| - | [Code](https://github.com/portrai-io/IAMSAM) | Portrai Inc. | A SAM application for the analysis of Spatial Transcriptomics.|\n\n#### 3D\n| Title | Presentation | Paper page | Project page | Code base | Affiliation | Description |\n| :-------------------:| :-------------------------------------------------------------------------------------------------------------:| :---------------------------------------------:| :-------------------------------------------------------------:| :-----------------------------------------------------------:| :------------:| :-----------------------------------------------------------------------------------------------------------------------------------------------------------:|\n| Point-SAM | ![img](https://github.com/zyc00/Point-SAM/blob/main/assets/indoor-ezgif.com-video-to-gif-converter.gif) | [arXiv](https://arxiv.org/abs/2406.17741) | [Page](https://point-sam.github.io) | [Code](https://github.com/zyc00/Point-SAM) | UCSD | An open-world 3D native promptable point-cloud segmentation method. |\n| SAMPro3D | ![img2](https://github.com/GAP-LAB-CUHK-SZ/SAMPro3D/blob/main/figures/teaser_ori.jpg) | [arXiv](https://arxiv.org/abs/2311.17707) | [Page](https://mutianxu.github.io/sampro3d/) | [Code](https://github.com/GAP-LAB-CUHK-SZ/SAMPro3D) | CUHKSZ, MSRA | A novel method to segment any 3D indoor scenes by applying the SAM to 2D frames, without need any training, tuning, distillation or 3D pretrained networks. |\n| Seal | ![img1](https://github.com/youquanl/Segment-Any-Point-Cloud/raw/main/docs/figs/demo.gif) | [arXiv](https://arxiv.org/abs/2306.09347) | [Page](https://ldkong.com/Seal) | [Code](https://github.com/youquanl/Segment-Any-Point-Cloud) | - | A framework capable of leveraging 2D vision foundation models for self-supervised learning on large-scale 3D point clouds. |\n| TomoSAM | ![img](https://github.com/fsemerar/SlicerTomoSAM/raw/main/TomoSAM/Resources/Media/tomosam_screenshot_1.png) | [arXiv](https://arxiv.org/pdf/2306.08609.pdf) | [Video Tutorial](https://www.youtube.com/watch?v=4nXCYrvBSjk) | [Code](https://github.com/fsemerar/SlicerTomoSAM) | - | An extension of 3D Slicer using the SAM to aid the segmentation of 3D data from tomography or other imaging techniques. |\n| SegmentAnythingin3D | ![img](https://user-images.githubusercontent.com/58475180/243306003-6135f473-3239-4721-9a79-15f7a7d11347.png) | [arXiv](https://arxiv.org/abs/2304.12308.pdf) | [Project](https://jumpat.github.io/SA3D/) | [Code](https://github.com/Jumpat/SegmentAnythingin3D) | - | A novel framework to Segment Anything in 3D, named SA3D. |\n\n#### Remote Sensing\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| RSPrompter | ![img](https://kyanchen.github.io/RSPrompter/resources/teaser.jpg) | [arXiv](https://arxiv.org/pdf/2306.16269.pdf) | [Project Page](https://kyanchen.github.io/RSPrompter/) | [Code](https://github.com/KyanChen/RSPrompter) | Beihang University | An automated instance segmentation approach for remote sensing images based on the SAM. |\n| SAM-CD | ![img](https://github.com/ggsDing/SAM-CD/blob/main/flowchart.png) | [arXiv](https://arxiv.org/abs/2309.01429) | - | [Code](https://github.com/ggsDing/SAM-CD) | PLA Information Engineering University | A sample-efficient change detection framework that employs SAM as the visual encoder. |\n| SAM-Road: Segment Anything Model for Road Network Graph Extraction | ![img](./imgs/sam_road_cover.png) | [arXiv](http://arxiv.org/abs/2403.16051) | - | [Code](https://github.com/htcr/sam_road) | Carnegie Mellon University | A simple and fast method applying SAM for vectorized large-scale road network graph extraction. It reaches state-of-the-art accuracy while being 40 times faster. |\n\n#### Tracking\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Follow Anything | ![img1](./imgs/Follow-Anything.png) | [arXiv](https://arxiv.org/abs/2308.05737) | [Page](https://huggingface.co/papers/2308.05737) | [Code](https://github.com/alaamaalouf/FollowAnything) | MIT, Harvard University | An open-vocabulary and multimodal model to detect, track, and follow any objects in real-time.|\n| Track-Anything | [Video](https://github.com/gaomingqi/Track-Anything/raw/master/assets/avengers.gif) | [arXiv](https://arxiv.org/abs/2304.11968) | - | [Code](https://github.com/gaomingqi/Track-Anything) | - | An interactive video object tracking and segmentation tool based on SAM and XMem.|\n| SAM-Track | [Video](https://camo.githubusercontent.com/149f974fc6e13f3764e30d843880fa1e15e0fbecf607f905805d84290ec87155/68747470733a2f2f7265732e636c6f7564696e6172792e636f6d2f6d6172636f6d6f6e74616c62616e6f2f696d6167652f75706c6f61642f76313638313731333039352f766964656f5f746f5f6d61726b646f776e2f696d616765732f796f75747562652d2d555068747066316b3648412d63303562353861633665623463343730303833316232623330373063643430332e6a7067) | [arXiv](https://arxiv.org/abs/2305.06558) | - | [Code](https://github.com/z-x-yang/Segment-and-Track-Anything) | Zhejiang University | A framework called Segment And Track Anything (SAMTrack) that allows users to precisely and effectively segment and track any object in a video.|\n\n#### Audio-visual Localization and Segmentation\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| AV-SAM | ![img1](./imgs/sam-av.png) | [arXiv](https://arxiv.org/pdf/2305.01836.pdf) | - | [Code](https://github.com/alaamaalouf/FollowAnything) | CMU | A simple yet effective audio-visual localization and segmentation framework based on the SAM.|\n\n#### Adversarial Attacks\n| Title | Presentation| Paper page | Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| Attack-SAM | - | [arXiv](https://arxiv.org/pdf/2305.00866.pdf) | - | - | KAIST | The first work of conduct a comprehensive investigation on how to attack SAM with adversarial examples. |\n\n#### Multimedia Forensics\n| Title | Presentation | Paper page | Project page | Code base | Affiliation | Description |\n| :---------------------------------------:| :------------------------------------------------------------------------------------:| :-----------------------------------------:| :------------:| :--------------------------------------------:| :-----------:| :---------------------------------------------------------------------------------------------------------------------------------:|\n| SAFIRE: Segment Any Forged Image Region | ![safire_image](https://github.com/mjkwon2021/SAFIRE/blob/main/figure_inference.png) | [arXiv](https://arxiv.org/abs/2412.08197) | - | [Code](https://github.com/mjkwon2021/SAFIRE) | KAIST | Extends SAM's point prompting capability to image forensics, enabling precise source-aware segmentation for forgery localization. |\n\n#### LLM and SAM\n| Title | Presentation | Paper page | Project page | Code base | Affiliation | Description |\n| :-----:| :-----------------------------------------------------------------------------:| :--------------------------------------------:| :--------------------------------------------------------:| :-----------------------------------------------:| :-----------:| :---------------------------------------------------------------------------------------------------------------------------------------------------------:|\n| LISA | ![img](https://github.com/JIA-Lab-research/LISA/blob/main/imgs/teaser.jpg) | [CVPR2024](https://arxiv.org/abs/2308.00692) | [Project Page](https://huggingface.co/papers/2308.00692) | [Code](https://github.com/dvlab-research/LISA) | CUHK | Large Language Instructed Segmentation Assistant: inherits LLM language generation while producing segmentation masks from complex implicit text queries. |\n| Sa2VA | ![img](https://github.com/bytedance/Sa2VA/blob/main/assets/images/teaser.jpg) | [arXiv](https://arxiv.org/abs/2501.04001) | [Project Page](https://huggingface.co/papers/2501.04001) | [Code](https://github.com/magic-research/Sa2VA) | - | Marries SAM 2 with LLaVA for dense grounded understanding of images and videos; unifies text, image, and video into a shared LLM token space. |\n\n#### Autonomous Driving\n| Title | Presentation | Paper page | Project page | Code base | Affiliation | Description |\n|:---:|:---:|:---:|:---:| :---:| :---:|:---:|\n| AD-SAM | - | [arXiv](https://arxiv.org/abs/2510.27047) | - | - | - | Fine-tuned SAM with dual-encoder and deformable decoder for semantic segmentation in autonomous driving scenes. |\n| SAM4UDASS | - | [arXiv](https://arxiv.org/abs/2401.08604) | - | - | - | Incorporates SAM into self-training UDA methods for refining pseudo-labels in unsupervised domain adaptive semantic segmentation for intelligent vehicles. |\n\n### Derivative Projects\n#### Image Segmentation task\n| Title | Presentation | Project pageγ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€| Code base | Affiliation | Description |\n| :--------------------------------:| :--------------------------------------------------------------------------------------------------------------------------------------------------:| :---------------------------------------------------------------------------------------------------------------------------------------------------------:| :-----------------------------------------------------------------------------:| :-----------:| :---------------------------------------------------------------------------------------------------:|\n| Grounded Segment Anything | ![img](https://github.com/IDEA-Research/Grounded-Segment-Anything/raw/main/assets/acoustics/gsam_whisper_inpainting_demo.png) | [Colab](https://github.com/camenduru/grounded-segment-anything-colab) \u0026 [Huggingface](https://huggingface.co/spaces/yizhangliu/Grounded-Segment-Anything) | [Code](https://github.com/IDEA-Research/Grounded-Segment-Anything) | - | Combining Grounding DINO and Segment Anything. |\n| GroundedSAM Anomaly Detection | ![img](https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection/raw/master/assets/framework.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/caoyunkang/GroundedSAM-zero-shot-anomaly-detection) | - | Grounding DINO + SAM to segment any anomaly. |\n| Semantic Segment Anything | ![img](https://github.com/fudan-zvg/Semantic-Segment-Anything/raw/main/figures/sa_225091_class_name.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/fudan-zvg/Semantic-Segment-Anything) | Fudan | A dense category annotation engine. |\n| Magic Copy | ![img](./imgs/magic.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/kevmo314/magic-copy) | - | Magic Copy is a Chrome extension that uses SAM. |\n| YOLO-World + EfficientViT SAM | ![img](https://github.com/Curt-Park/yolo-world-with-efficientvit-sam/assets/14961526/326bde19-d535-4be5-829e-782fce0c1d00) | πŸ€— [HuggingFace Space](https://huggingface.co/spaces/curt-park/yolo-world-with-efficientvit-sam)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€| [Code](https://github.com/Curt-Park/yolo-world-with-efficientvit-sam) | - | Efficient open-vocabulary object detection and segmentation with YOLO-World + EfficientViT SAM. |\n| Segment Anything with Clip | ![img](https://user-images.githubusercontent.com/14961526/230437084-79ef6e02-a254-421e-bd4c-32e87415c623.png) | πŸ€— [HuggingFace Space](https://huggingface.co/spaces/curt-park/segment-anything-with-clip)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€| [Code](https://github.com/Curt-Park/segment-anything-with-clip) | - | SAM + CLIP. |\n| SAM-Clip | ![img](https://github.com/maxi-w/CLIP-SAM/blob/main/assets/example-segmented.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/maxi-w/CLIP-SAM) | - | SAM + CLIP. |\n| Prompt Segment Anything | ![img](https://github.com/RockeyCoss/Prompt-Segment-Anything/blob/master/assets/example4.jpg) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/RockeyCoss/Prompt-Segment-Anything) | - | SAM + Zero-shot Instance Segmentation. |\n| RefSAM | - | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/helblazer811/RefSAM) | - | Evaluating the basic performance of SAM on the Referring Image segmentation task. |\n| SAM-RBox | ![img](https://user-images.githubusercontent.com/79644233/230732578-649086b4-7720-4450-9e87-25873bec07cb.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/Li-Qingyun/sam-mmrotate) | - | An implementation of SAM for generating rotated bounding boxes with MMRotate. |\n| Open Vocabulary Segment Anything | ![img1](./imgs/ovsa.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/ngthanhtin/owlvit_segment_anything) | - | An interesting demo by combining OWL-ViT of Google and SAM. |\n| SegDrawer | ![img1](https://github.com/lujiazho/SegDrawer/blob/main/example/demo.gif)![img](https://github.com/lujiazho/SegDrawer/blob/main/example/demo1.gif) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/lujiazho/SegDrawer) | - | Simple static web-based mask drawer, supporting semantic drawing with SAM. |\n| AnyLabeling | ![](https://raw.githubusercontent.com/vietanhdev/anylabeling/master/assets/screenshot.png) | [YoutubeDemo](https://www.youtube.com/watch?v=5qVJiYNX5Kk)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€| [Code](https://github.com/vietanhdev/anylabeling) | - | SAM + Labelme + LabelImg + Auto-labeling. |\n| ISAT with segment anything | ![](https://github.com/yatengLG/ISAT_with_segment_anything/blob/master/display/%E6%A0%87%E6%B3%A8.gif) | [YoutubeDemo](https://www.youtube.com/watch?v=yLdZCPmX-Bc) [BiliBili Demo](https://www.bilibili.com/video/BV1or4y1R7EJ/)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€| [Code](https://github.com/yatengLG/ISAT_with_segment_anything) | - | Labeling tool by SAM, supports SAM, sam-hq, MobileSAM, EdgeSAM etc. |\n| Annotation Anything Pipeline | ![img](https://user-images.githubusercontent.com/48062034/231222391-5423f45c-6133-45f0-81b1-be0cdaeda545.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/Yuqifan1117/Annotation-anything-pipeline) | - | GPT + SAM. |\n| Roboflow Annotate | ![roboflow-sam-optimized-faster](https://user-images.githubusercontent.com/870796/231834341-b0674467-ddc9-4996-b5ae-2d40dcc22409.gif) | [App](https://app.roboflow.com)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Blog](https://blog.roboflow.com/label-data-segment-anything-model-sam/) | Roboflow | SAM-assisted labeling for training computer vision models. |\n| SALT | ![img](https://github.com/anuragxel/salt/raw/main/assets/how-it-works.gif) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/anuragxel/salt) | - | A tool that adds a basic interface for image labeling and saves the generated masks in COCO format. |\n| SAM U Specify | ![img](./imgs/sus.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/MaybeShewill-CV/segment-anything-u-specify) | - | Use SAM and CLIP model to segment unique instances you want. |\n| SAM web UI | ![img](https://github.com/Kingfish404/segment-anything-webui/raw/main/assets/demo.gif) | [App](https://segment-anything-webui.vercel.app/)γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/Kingfish404/segment-anything-webui/) | - | A web interface for the SAM. |\n| Finetune Anything | ![img](https://user-images.githubusercontent.com/67993288/230864865-db8810fd-9f0c-4f3e-81b1-8753b5121d03.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/ziqi-jin/finetune-anything) | - | A class-aware one-stage tool for training fine-tuning models based on SAM. |\n| NanoSAM | ![img](https://github.com/NVIDIA-AI-IOT/nanosam/blob/main/assets/basic_usage_out.jpg) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/NVIDIA-AI-IOT/nanosam) | NVIDIA | A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT. |\n| Segment-Anything-UI | ![img](https://github.com/branislavhesko/segment-anything-ui/blob/main/assets/example.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/branislavhesko/segment-anything-ui) | - | A PySide6 based annotation tool for Segment Anything. |\n| Segment-Anything-2-UI | ![img](https://github.com/branislavhesko/segment-anything-2-ui/blob/main/segment_anything_2_ui/assets/example.png) | -γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€γ€€ | [Code](https://github.com/branislavhesko/segment-anything-2-ui) | - | A PySide6 based annotation tool for Segment Anything 2. Video tracking with multiple objects. |\n\n#### Video Segmentation task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| MetaSeg | ![img](https://github.com/kadirnar/segment-anything-pip/releases/download/v0.2.2/metaseg_demo.gif) | [HuggingFace](https://huggingface.co/spaces/ArtGAN/Segment-Anything-Video) | [Code](https://github.com/kadirnar/segment-anything-video) | - | SAM + Video. |\n| SAM-Track | [Video](https://www.youtube.com/watch?v=UPhtpf1k6HA\u0026feature=youtu.be\u0026themeRefresh=1) | [YoutubeDemo](https://www.youtube.com/watch?v=Xyd54AngvV8) | [Code](https://github.com/z-x-yang/Segment-and-Track-Anything) | Zhejiang University | This project, which is based on SAM and DeAOT, focuses on segmenting and tracking objects in videos. |\n\n#### Medical image Segmentation task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| SAM in Napari | [Video](https://www.youtube.com/watch?v=OPE1Xnw487E)| - | [Code](https://github.com/MIC-DKFZ/napari-sam) | - | Segment anything with Napari integration of SAM.|\n| SAM Medical Imaging | ![img](https://miro.medium.com/v2/resize:fit:720/format:webp/1*_0vvAXd8LnMu2t0rEt5a0Q.png)| - | [Code](https://github.com/amine0110/SAM-Medical-Imaging) | - | SAM for Medical Imaging.|\n\n#### Inpainting task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| SegAnythingPro | ![img](https://camo.githubusercontent.com/7d5fb67ffcd6c209cf22ffe302d95b3b46d36b92116fe216022bf2a359c4b588/68747470733a2f2f6a6968756c61622e636f6d2f676f646c792f666765722f2d2f7261772f6d61696e2f696d616765732f323032332f30342f31315f31325f345f34325f32303233303431313132303433392e706e67)| - | [Code](https://github.com/jinfagang/Disappear) | - | SAM + Inpainting/Replacing.|\n\n#### 3D task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| 3D-Box | ![img](https://github.com/dvlab-research/3D-Box-Segment-Anything/raw/main/images/sam-voxelnext.png)| - | [Code](https://github.com/dvlab-research/3D-Box-Segment-Anything) | - | SAM is extended to 3D perception by combining it with VoxelNeXt.|\n| Anything 3D Novel View | ![img](https://github.com/Anything-of-anything/Anything-3D/raw/main/novel-view/assets/1.jpeg)| - | [Code](https://github.com/Anything-of-anything/Anything-3D) | - | SAM + [Zero 1-to-3](https://github.com/cvlab-columbia/zero123).|\n| Any 3D Face | ![img](https://github.com/Anything-of-anything/Anything-3D/raw/main/AnyFace3D/assets/celebrity_selfie/mask_2.jpg)![img](https://github.com/Anything-of-anything/Anything-3D/raw/main/AnyFace3D/assets/celebrity_selfie/2.gif)| - | [Code](https://github.com/Anything-of-anything/Anything-3D) | - | SAM + [HRN](https://younglbw.github.io/HRN-homepage/).|\n| Segment Anything 3D | ![img](https://github.com/Pointcept/SegmentAnything3D/raw/main/docs/0.png) | - | [Code](https://github.com/Pointcept/SegmentAnything3D) | Pointcept | Extending Segment Anything to 3D perception by transferring the segmentation information of 2D images to 3D space.|\n\n#### Image Generation task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| Edit Anything | ![img](https://github.com/sail-sg/EditAnything/blob/main/images/edit_sample1.jpg) | - | [Code](https://github.com/sail-sg/EditAnything) | - | Edit and Generate Anything in an image.|\n| Image Edit Anything | ![img](https://user-images.githubusercontent.com/37614046/230707537-206c0714-de32-41cd-a277-203fd57cd300.png)| - | [Code](https://github.com/feizc/IEA) | - | Stable Diffusion + SAM.|\n| SAM for Stable Diffusion Webui | ![img](./imgs/samsdb.png)| - | [Code](https://github.com/continue-revolution/sd-webui-segment-anything) | - | Stable Diffusion + SAM.|\n\n#### Remote Sensing task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| Earth Observation Tools | ![img](https://github.com/aliaksandr960/segment-anything-eo/raw/main/title_sameo.png?raw=true) | [Colab](https://colab.research.google.com/drive/1RC1V68tD1O-YissBq9nOvS2PHEjAsFkA?usp=share_link) | [Code](https://github.com/aliaksandr960/segment-anything-eo) | - | SAM + Remote Sensing. |\n\n#### Moving Object Detection task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| Moving Object Detection | ![img](https://camo.githubusercontent.com/cd073471951017a15cd445062d196242a446eb20acd90b2afa1728f239465fc7/687474703a2f2f7777772e616368616c646176652e636f6d2f70726f6a656374732f616e797468696e672d746861742d6d6f7665732f766964656f732f5a584e36412d747261636b65642d776974682d6f626a6563746e6573732d7472696d6d65642e676966) | - | [Code](https://github.com/achalddave/segment-any-moving) | - | SAM + Moving Object Detection. |\n\n#### OCR task\n| Title | Presentation| Project page | Code base | Affiliation| Description|\n|:---:|:---:|:---:|:---:| :---:| :---:|\n| OCR-SAM | ![img](https://github.com/yeungchenwa/OCR-SAM/raw/main/imgs/sam_vis.png) | [Blog](https://www.zhihu.com/question/593914819/answer/2976012032)| [Code](https://github.com/yeungchenwa/OCR-SAM) | - | Optical Character Recognition with SAM. |\n\n### front-end framework\n\n#### SAMJS\n| Title | Presentation | Project page | Code base | Affiliation | Description |\n| :-----:| :--------------------------------------------------------------------------------------------------------:| :--------------------------------------:| :---------------------------------------:| :-----------:| :---------------------------------------------------------------------------:|\n| SAMJS | ![samjs](https://mdn.alipayobjects.com/huamei_qa8qxu/afts/img/A*6rjpTIjg4cUAAAAAAAAAAAAADmJ7AQ/original) | [demo](http://samjs.antv.vision/demos) | [Code](https://github.com/antvis/SAMJS) | - | JS SDK for SAM, Support remote sensing data segmentation and vectorization. |\n\n## Acknowledgement\nSome of the presentations in this repository are borrowed from the original author, and we are very thankful for their contribution.\n\n## License\nThis project is released under the MIT license. Please see the [LICENSE](LICENSE) file for more information.\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/hedlen%2Fawesome-segment-anything/projects"}