https://github.com/JerryX1110/awesome-segment-anything-extensions
Segment-anything related awesome extensions/projects/repos.
https://github.com/JerryX1110/awesome-segment-anything-extensions
List: awesome-segment-anything-extensions
application awesome awesome-list caption-anything computer-vision foundation-models generation generative-model image-segmentation machine-learning object-detection segment-anything segment-anything-meta segmentation style-transfer tracking
Last synced: 6 months ago
JSON representation
Segment-anything related awesome extensions/projects/repos.
- Host: GitHub
- URL: https://github.com/JerryX1110/awesome-segment-anything-extensions
- Owner: JerryX1110
- Created: 2023-04-10T03:24:31.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2023-06-28T14:46:53.000Z (almost 2 years ago)
- Last Synced: 2024-12-02T06:02:29.552Z (6 months ago)
- Topics: application, awesome, awesome-list, caption-anything, computer-vision, foundation-models, generation, generative-model, image-segmentation, machine-learning, object-detection, segment-anything, segment-anything-meta, segmentation, style-transfer, tracking
- Homepage:
- Size: 64.5 KB
- Stars: 343
- Watchers: 10
- Forks: 13
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- Awesome-Segment-Anything - Awesome Segment-Anything Extensions - segment-anything-extensions.svg?logo=github&label=Stars) (2 Project & Toolbox<span id='tool'>)
- Awesome-Segment-Anything - JerryX1110/Awesome-segment-anything-extensions
- ultimate-awesome - awesome-segment-anything-extensions - Segment-anything related awesome extensions/projects/repos. (Other Lists / Julia Lists)
README
# Awesome-segment-anything-extensions [](https://awesome.re) [](https://github.com/topics/awesome)
Segment-anything related awesome extensions/projects/repos/applications.
Welcome to starts ⭐ & comments 💹 & sharing 😀 !!
```diff
- 2023.4.9: Recent works/projects (from 2023)
- welcome to add if any information misses. 😎
```---
## Recent Works
- Segment Anything Model (SAM) official [Repo](https://github.com/facebookresearch/segment-anything)The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

- Grounded-Segment-Anything (Combination of Ground-DINO and Segment-Anything) [Repo](https://github.com/IDEA-Research/Grounded-Segment-Anything#grounded-segment-anything)

- Segment-Any-Anomaly + (SAM + hybrid prompt regularization for zero-shot anomaly detection)[ArXiV](https://arxiv.org/abs/2305.10724)


- Segment Any Point Cloud Sequences (SAM for self-supervised learning on large-scale 3D point clouds) [Repo](https://github.com/youquanl/Segment-Any-Point-Cloud) [ArXiv](https://arxiv.org/abs/2306.09347) [Page](https://ldkong.com/Seal)

- Segment-Any-Anomaly (SAM + GroudingDINO for anomaly detection)[Repo](https://github.com/caoyunkang/Segment-Any-Anomaly)

- Segment and Track Anything (SAM-Track) [Repo](https://github.com/z-x-yang/Segment-and-Track-Anything) [ArXiv](https://arxiv.org/abs/2305.06558)
- Inpaint/Remove/Fill-Anything (image inpainting meets sam) [Repo](https://github.com/geekyutao/Inpaint-Anything)

- SEEM: Segment Everything Everywhere All at Once [Repo](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once)

- Roboflow Annotate Smart Polygon is a free, automated image annotation tool powered by Segment-Anything [Blog](https://blog.roboflow.com/label-data-segment-anything-model-sam/), [App](https://app.roboflow.com)
https://user-images.githubusercontent.com/870796/231829898-7219aba8-2931-42ae-82a4-9b2a91b02d0a.mp4
- Image Editing Anything (SAM + CLIP +StableDiffusion) [Repo](https://github.com/feizc/IEA)

- Semantic Segment Anything (SAM for semantic seg) [Repo](https://github.com/fudan-zvg/Semantic-Segment-Anything)

- segment-anything-with-clip (SAM + CLIP) [Repo](https://github.com/Curt-Park/segment-anything-with-clip)
- magic-copy (use SAM for foreground mask segmentation) [Repo](https://github.com/kevmo314/magic-copy)
- EditAnything (SAM for image generation) [Repo](https://github.com/sail-sg/EditAnything)

- Prompt-Segment-Anything (use SAM for instance segmentation) [Repo](https://github.com/RockeyCoss/Prompt-Segment-Anything)
- RefSAM (use SAM for refer image segmentation) [Repo](https://github.com/helblazer811/RefSAM)
- sam-mmrotate(use SAM for generating rotated bounding boxes with MMRotate) [Repo](https://github.com/Li-Qingyun/sam-mmrotate)
- Fast-SAM (fast segment-anything) [repo](https://github.com/CASIA-IVA-Lab/FastSAM)

- Mobile-SAM (faster segment-anything) [repo](https://github.com/ChaoningZhang/MobileSAM)

- Disappear(use SAM for foreground removal) [Repo](https://github.com/jinfagang/Disappear)
- Segment-anything-with-image-captioning(sam + image caption) [Repo](https://github.com/bnabis93/segment-anything-image-search)
- Open-vocabulary-Segment-Anything (OWL-ViT of Google + Segment Anything of Meta) [Repo](https://github.com/ngthanhtin/owlvit_segment_anything)

- semantic drawing with Segment Anything Model (SAM for mask drawing/editing) [Repo](https://github.com/lujiazho/SegDrawer)

- Annotation-anything-pipeline (GPT+SAM) [Repo](https://github.com/Yuqifan1117/Annotation-anything-pipeline)
- MOTSAM (MOT+SAM->MOTS)[Repo](https://github.com/BingfengYan/MOTSAM)
- SAMCOD (SAM for Camouflaged Object Detection) [Paper](https://arxiv.org/abs/2304.04709) [Repo](https://github.com/luckybird1994/SAMCOD)
- Segment Anything Model (SAM) in Napari (SAM + Napari) [Repo](https://github.com/MIC-DKFZ/napari-sam)

- inpainting-anything (SAM + inpainting) [Repo](https://github.com/geekyutao/Inpaint-Anything)

- segment-anything-eo (Earth observation tools for Meta AI Segment Anything) [Repo](https://github.com/aliaksandr960/segment-anything-eo)

- Segment Anything for Stable Diffusion Webui (helping stable diffusion webui users to use segment anything to do stable diffusion inpainting) [Repo]()

- Napari plugin of Segment Anything Model (SAM) [Repo] (https://github.com/JoOkuma/napari-segment-anything)

- segment-anything-and-name-it (Visual GPT + SAM) [Repo](https://github.com/Cheems-Seminar/segment-anything-and-name-it)

- AnyLabeling = LabelImg + Labelme + Improved UI + Auto-labeling [Repo](https://github.com/vietanhdev/anylabeling)

- Caption-anything (Segment Anything + Visual Captioning + ChatGPT) [Repo](https://github.com/ttengwang/Caption-Anything)

- Segment-anything-u-specify (using sam + clip to segment anything u specify) [Repo](https://github.com/MaybeShewill-CV/segment-anything-u-specify)

- OCR-SAM (SAM for Text, Text Removal and Text Inpainting) [Repo](https://github.com/yeungchenwa/OCR-SAM)


- finetune-anything (fine-tuning of SAM ) [Repo]()

- grounded-segment-anything-colab [Repo](https://github.com/camenduru/grounded-segment-anything-colab)

- SAM Medical Imaging [Repo](https://github.com/amine0110/SAM-Medical-Imaging)

- Segment Anything Prompt (SAM + GroundDINO + Stable Diffusion for foreground removal and background inpainting) [Repo](https://github.com/jinfagang/SegAnythingPro)

- Transform Image Into Unique Paragraph (ChatGPT+SAM+BLIP) [Repo](https://github.com/showlab/Image2Paragraph)

- LIME-SAM (SAM + Explainable Artificial Intelligence) [Repo](https://github.com/jaydeep-work/LIME-SAM)

- sam-with-mmdet (SAM+MMDetection) [Repo](https://github.com/liuyanyi/sam-with-mmdet)

- open-tracking (sam + tracking) [Repo](https://github.com/open-mmlab/playground/#-open-tracking)

- 3D-Box via Segment Anything (sam for 3D Detection) [Repo](https://github.com/dvlab-research/3D-Box-Segment-Anything)

- Anything-3D (Segment-Anything + 3D. Let's lift the anything to 3D) [Repo](https://github.com/Anything-of-anything/Anything-3D)


- Transfer-Any-Style (SAM for style transfer) [Repo](https://github.com/Anything-of-anything/Transfer-Any-Style)

- Paint-anything (sam for drawing) [Repo](https://github.com/Huage001/Paint-Anything)

- track-anything (VOS + sam)[Repo](https://github.com/gaomingqi/Track-Anything)

- SAM-medical (SAM for medocal image segmentation)[Repo](https://github.com/hitachinsk/SAM-Medical)
- relate-anything (relation empowered via SAM) [Repo](https://github.com/Luodian/RelateAnything)

- Count Anything (SAM for counting) [Repo](https://github.com/ylqi/Count-Anything)

- ShowAnything (SAM + SD for editing) [Repo](https://github.com/showlab/ShowAnything)

- MedSAM (SAM for medicine, training tutorial) [Repo](https://github.com/bowang-lab/MedSAM#model-training-video-tutorial)
- Personalize-SAM (Personalize Segment Anything with 1 Shot in 10 Seconds) [Repo](https://github.com/ZrrSkywalker/Personalize-SAM)
- Segment Any Moving Object with Moving Ego Vehicle (SAM for multi-object segmentation) [arXiv](https://arxiv.org/pdf/2305.00126.pdf)
- Customized Segment Anything Model for Medical Image Segmentation (SAM+LoRA fot Medical Segmentation) [ArXiv](https://arxiv.org/pdf/2304.13785.pdf)

- Instruct to Act (SAM+OpenCLIP for robotics application) [Repo](https://github.com/OpenGVLab/Instruct2Act)

- finetune-anything (SAM finetuning) [Repo](https://github.com/ziqi-jin/finetune-anything)

- SAMScore (semantic Structural Similarity Metric for Image Translation Evaluation) [ArXiv](https://arxiv.org/pdf/2305.15367.pdf)

- Detect-AnyShadow (SAM for shadow det) [Repo](https://github.com/harrytea/Detect-AnyShadow)

- SAD: Segment Any RGBD (SAM+Depth / SAM for RGBD) [Repo](https://github.com/Jun-CEN/SegmentAnyRGBD)

- SAM-HQ: Segment Anything in High Quality (High Quality Mask with SAM) [Repo](https://github.com/SysCV/SAM-HQ)

- Calib-anything (SAM for calibration optimization) [Repo](https://github.com/OpenCalib/CalibAnything)

## Relevant Repos
- Towards Segmenting Anything That Moves [Repo](https://github.com/achalddave/segment-any-moving)

- SegGPT: Segmenting Everything In Context [Repo](https://github.com/baaivision/Painter)

- Painter [Repo](https://github.com/baaivision/Painter)

- Stable Diffusion (High-Resolution Image Synthesis with Latent Diffusion Models) [Repo](https://github.com/CompVis/stable-diffusion)

- ControlNet (Adding Conditional Control to Text-to-Image Diffusion Models.) [Repo](https://github.com/lllyasviel/ControlNet) [Paper](https://arxiv.org/abs/2302.05543)

- image2text powered by CLIP and BLIP [Repo](https://github.com/pharmapsychotic/clip-interrogator)